© 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. 34-GEMMASCOPE-RES-131K
    7. 57966
    Prev
    Next
    INDEX
    Explanations

    Supreme Court, public licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    getJSON
    -0.79
     tặng
    -0.73
     tortilla
    -0.68
    ceps
    -0.65
     packets
    -0.65
    ENDED
    -0.63
    plona
    -0.63
    넷
    -0.62
    ENODEV
    -0.62
    виться
    -0.62
    POSITIVE LOGITS
     edilen
    0.66
    ऐ
    0.65
     Пан
    0.64
     gql
    0.62
     fait
    0.62
     Zan
    0.61
    ByDate
    0.61
    埔
    0.61
    聪明
    0.60
    ienze
    0.60
    Activations Density 0.095%

    No Known Activations