© 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. 57807
    Prev
    Next
    INDEX
    Explanations

    software, license, manual, corp

    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
     demonstr
    -0.76
    vek
    -0.73
    豁
    -0.69
    ratto
    -0.68
    杖
    -0.68
    Aven
    -0.68
    犀
    -0.67
    IndexOf
    -0.67
    ONDON
    -0.66
     Cron
    -0.66
    POSITIVE LOGITS
    申請
    0.73
     tabletop
    0.70
     清水
    0.65
     ملي
    0.65
    athies
    0.64
     cámaras
    0.63
    paisaje
    0.62
    變成
    0.62
     Lakeside
    0.61
     تاریخی
    0.61
    Activations Density 0.077%

    No Known Activations