© 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. 68471
    Prev
    Next
    INDEX
    Explanations

    Bridget Jones Diary, Bridget M. McCormack

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

    The neuron fires on capitalized mid‐sentence tokens—proper names, acronyms, or branded/library terms.

    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
    );
    -3.33
    {
    -3.28
     you
    -2.70
     '
    -2.67
     diversas
    -2.64
    決して
    -2.64
    咴
    -2.58
    _
    -2.56
    肫
    -2.55
     diversos
    -2.52
    POSITIVE LOGITS
    because
    2.66
    宬
    2.50
    henswürdigkeiten
    2.48
    at
    2.42
    ↑↑↑</
    2.36
    ✁
    2.31
    ꯖ
    2.30
    🎍
    2.27
    ettür
    2.23
    ’，
    2.19
    Activations Density 0.010%

    No Known Activations