© 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. 79032
    Prev
    Next
    INDEX
    Explanations

    function arguments and variables

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

    The neuron activates on identifiers in function parameter lists (e.g. argument names in callback signatures).

    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
     while
    -0.92
    ща
    -0.90
    ترنت
    -0.83
    !,
    -0.79
     большинство
    -0.77
    лого
    -0.77
     بيانات
    -0.76
     диамет
    -0.74
    **
    -0.73
    ...,
    -0.73
    POSITIVE LOGITS
     också
    0.97
     _)
    0.96
    Lä
    0.94
    合わせる
    0.93
    taan
    0.91
     ttk
    0.91
    いま
    0.90
    seguir
    0.90
     ASPECTS
    0.88
    ૌ
    0.88
    Activations Density 0.020%

    No Known Activations