© 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. 10-GEMMASCOPE-RES-131K
    7. 113252
    Prev
    Next
    INDEX
    Explanations

    code start or keywords

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

    double underscore tokens in code (like `__DIR__`, `__FILE__`, or `__all__`).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is triggered by tokens containing double underscores (e.g. “__”, “__DIR__”, “__FILE__”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    providedIn
    -2.55
    Ꮏ
    -2.38
    珰
    -2.30
    傀
    -2.28
    itizing
    -2.25
    慊
    -2.23
     itſelf
    -2.19
     samme
    -2.17
    swire
    -2.16
    銪
    -2.16
    POSITIVE LOGITS
    [
    2.64
    ,.
    2.64
    i
    2.63
    >
    2.63
     a
    2.56
    *
    2.48
    }
    2.45
    "
    2.44
    <
    2.42
    +
    2.41
    Activations Density 0.004%

    No Known Activations