Abstract
Recent work has identified a human brain network specialized for abstract formal reasoning (Kean et al., 2025). Does the same hold true in language models? To answer this question, we introduce the minimal viable subspace (MVS) method, which searches for the lowest-rank activation subspace at a layer that preserves task performance when everything outside that subspace is ablated. Using MVS, we demonstrate low-rank subspaces supporting logical inference on Gemma and Qwen models. Furthermore, these subspaces exhibit a clear dissociation from model capacities on other tasks, such that retaining these late logic subspaces preserves inference while impairing factual knowledge, working memory, cognitive control, and arithmetic. Conversely, ablating them reduces logical inference accuracy to chance while largely sparing these other capacities. Our results suggest a functionally localizable core machinery for logic akin to that in the human brain.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Kean, H., & Boix-Adsera, E. (2026). Logical subspace in LLMs. https://omanscience.com/en/articles/logical-subspace-in-llms
MLA 9
Kean, Hope, and Enric Boix-Adsera. "Logical subspace in LLMs." https://omanscience.com/en/articles/logical-subspace-in-llms.
Chicago (author–date)
Kean, Hope, and Enric Boix-Adsera. 2026. "Logical subspace in LLMs." https://omanscience.com/en/articles/logical-subspace-in-llms.
Harvard
Kean, H. and Boix-Adsera, E. (2026) 'Logical subspace in LLMs', Available at: https://omanscience.com/en/articles/logical-subspace-in-llms.
Vancouver
Kean H, Boix-Adsera E. Logical subspace in LLMs. https://omanscience.com/en/articles/logical-subspace-in-llms
IEEE
H. Kean, and E. Boix-Adsera, "Logical subspace in LLMs," https://omanscience.com/en/articles/logical-subspace-in-llms.