© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84448
    Prev
    Next
    INDEX
    Explanations

    code delimitations or programming terms

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

    This neuron fires on tokens involved in type checks and casts (e.g. instanceof, C-style casts, Node.TYPE constants, the `->` member-access after casting, and `typeof` usage).

    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
    неве
    -0.92
     the
    -0.91
    ergic
    -0.90
     himself
    -0.88
    olysis
    -0.88
     فعل
    -0.87
     wirklich
    -0.86
     our
    -0.86
     ۶
    -0.84
    sqrt
    -0.84
    POSITIVE LOGITS
    пример
    0.98
    zembro
    0.97
    Только
    0.93
    pellier
    0.91
     semplicemente
    0.91
    ệu
    0.91
     ecuador
    0.90
     フォント
    0.90
     этого
    0.90
    elola
    0.89
    Activations Density 0.001%

    No Known Activations