© 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. 22-GEMMASCOPE-RES-131K
    7. 25386
    Prev
    Next
    INDEX
    Explanations

    callback and completion handlers

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

    The neuron fires most strongly on callback identifiers and related promise‐style function arguments in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     условий
    -0.88
     jetzt
    -0.86
     existing
    -0.85
    互联网档案馆
    -0.85
    ┫
    -0.84
     میتوان
    -0.84
     señala
    -0.83
     now
    -0.82
    DEPORT
    -0.82
     activate
    -0.82
    POSITIVE LOGITS
    mbler
    1.00
    楽天
    0.99
     goederen
    0.93
    Функ
    0.93
    ielder
    0.91
    结果
    0.91
     mochilas
    0.91
    loxy
    0.90
    ผล
    0.90
    您好
    0.90
    Activations Density 0.017%

    No Known Activations