© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26118
    Prev
    Next
    INDEX
    Explanations

    mathematical function definitions and structures

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on LaTeX/math‐formatting symbols (e.g. curly brace “{”, the “underbrace” command) and logical connective “iff.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ستار
    -1.05
    はその
    -0.97
    があります
    -0.95
    jącego
    -0.93
     allerede
    -0.90
     spørs
    -0.89
     eredeti
    -0.88
    くれました
    -0.88
     cæ
    -0.87
     from
    -0.86
    POSITIVE LOGITS
    ()<<
    1.10
     برای
    1.10
    <!--
    1.02
    emore
    1.01
    Decide
    1.01
    cussed
    0.96
    —-
    0.94
     Ballo
    0.93
    多么
    0.91
    ar
    0.90
    Activations Density 0.001%

    No Known Activations