© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91682
    Prev
    Next
    INDEX
    Explanations

    # CHECK instructions

    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
     hydrothermal
    -0.73
    mitter
    -0.73
     Werkstatt
    -0.71
    timeouts
    -0.70
     дії
    -0.70
     sero
    -0.70
    ⅽ
    -0.68
     Fiscalía
    -0.68
     lower
    -0.67
     захворю
    -0.67
    POSITIVE LOGITS
     users
    0.86
    users
    0.79
     Uses
    0.73
    使用者
    0.72
     Exercises
    0.71
    undef
    0.69
     Bonif
    0.68
     Calla
    0.68
    getNode
    0.68
     Wap
    0.68
    Activations Density 0.045%

    No Known Activations