© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49335
    Prev
    Next
    INDEX
    Explanations

    function call, prototype, arguments

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

    This neuron fires on JavaScript source‐code syntax, especially function definitions and related punctuation in code blocks.

    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
    SetBool
    -0.90
    ə
    -0.81
    プレス
    -0.77
    יע
    -0.73
    EnumMember
    -0.71
    Glej
    -0.71
     hóa
    -0.71
    ೆ
    -0.71
    温柔
    -0.70
    त
    -0.70
    POSITIVE LOGITS
     displayName
    0.85
    toString
    0.84
     Function
    0.84
     ater
    0.83
     Tá
    0.81
     interrup
    0.81
     toString
    0.81
     func
    0.81
     ór
    0.81
     (...
    0.81
    Activations Density 0.040%

    No Known Activations