© 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. 84140
    Prev
    Next
    INDEX
    Explanations

    programming types generic parameters

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

    The neuron primarily detects comma separators, especially those used in generic type parameter lists.

    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
    {*}
    -1.88
     creciendo
    -1.70
    😻
    -1.67
     personnal
    -1.66
     welkom
    -1.65
     sinds
    -1.63
     เก็
    -1.61
    猡
    -1.59
     rekening
    -1.59
     kj
    -1.57
    POSITIVE LOGITS
     of
    2.84
     that
    2.61
     can
    2.20
     who
    2.19
    </strong>
    2.14
    </u>
    2.08
     Possibly
    2.03
     That
    2.02
    是怎么回事
    1.88
     potentially
    1.87
    Activations Density 0.007%

    No Known Activations