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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 23725
    Prev
    Next
    INDEX
    Explanations

    function declarations

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

    The neuron fires on opening‐parenthesis tokens in code (i.e. the “(” used in function definitions and calls).

    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
    riotic
    -0.77
    resiasi
    -0.74
     プール
    -0.73
    dée
    -0.72
    /'
    -0.71
     them
    -0.71
    ToReturn
    -0.70
    牲
    -0.70
    цька
    -0.70
     will
    -0.69
    POSITIVE LOGITS
    unused
    1.63
     unused
    1.39
    UNUSED
    1.36
    Unused
    1.28
     Unused
    1.05
     ignored
    1.03
     dummy
    1.02
    dummy
    0.99
    ignored
    0.97
    电动
    0.92
    Activations Density 0.028%

    No Known Activations