© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3390
    Prev
    Next
    INDEX
    Explanations

    method parameters and return types

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

    This neuron activates on parameter names in function or method signatures (i.e. identifiers like “s,” “start,” “count,” “after,” “property,” “position,” “keyCode,” etc.).

    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
     also
    -1.13
    ;
    -1.03
     this
    -0.98
    ::*;
    -0.98
     then
    -0.94
    。
    -0.94
    의
    -0.93
     many
    -0.93
    namental
    -0.91
    ();
    -0.91
    POSITIVE LOGITS
    Interes
    1.04
     DIDN
    0.99
    Lä
    0.98
    なかな
    0.98
    素敵
    0.97
     tchèque
    0.93
    はなく
    0.93
    素晴らしい
    0.93
    素敵な
    0.92
    extremely
    0.91
    Activations Density 0.014%

    No Known Activations