© 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. 34-GEMMASCOPE-RES-131K
    7. 62876
    Prev
    Next
    INDEX
    Explanations

    function definitions and variable declarations

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

    This neuron fires on code‐related keywords and constructs (e.g. “function,” “return,” “var,” “recursion,” “sum,” “total”)—in other words, it spots programming‐language syntax.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    比べると
    -1.06
     Konkur
    -0.84
    sätzlich
    -0.83
    比べて
    -0.81
    polator
    -0.77
    тке
    -0.75
     Yiddish
    -0.75
     толкова
    -0.74
     wok
    -0.73
     Wishing
    -0.73
    POSITIVE LOGITS
    geq
    0.84
     viime
    0.80
     PUBLICATIONS
    0.79
    omsday
    0.78
    Needless
    0.78
    ほうが
    0.77
    =(
    0.77
    __(
    0.76
     lĩnh
    0.76
    /<
    0.75
    Activations Density 0.033%

    No Known Activations