© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72307
    Prev
    Next
    INDEX
    Explanations

    UI elements and categories

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

    The neuron strongly activates on CamelCase or otherwise capitalized code identifiers (e.g. class, widget, and variable names).

    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
    行って
    -2.25
    );
    -2.06
     功效
    -2.03
    垆
    -1.97
    遭
    -1.96
     是否
    -1.93
    魨
    -1.91
     pentru
    -1.91
    聍
    -1.89
     either
    -1.88
    POSITIVE LOGITS
    </strong>
    2.63
    ↵
    2.05
     superfluous
    2.03
    ۀ
    1.98
    1.97
     incluido
    1.95
     lags
    1.93
     altes
    1.91
    出
    1.88
     trouvez
    1.86
    Activations Density 0.001%
    No Known Activations