© 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. 30701
    Prev
    Next
    INDEX
    Explanations

    code, file paths, and technical descriptions

    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
    getPassword
    -0.70
    Мак
    -0.67
     thảm
    -0.66
     converti
    -0.66
    berd
    -0.65
     SBP
    -0.65
     nghệ
    -0.64
    ikaze
    -0.64
     dovrà
    -0.64
    Gentlemen
    -0.63
    POSITIVE LOGITS
    pidou
    0.72
    palm
    0.72
     Seneca
    0.71
     rendering
    0.70
    ƈ
    0.67
     render
    0.66
     stitching
    0.65
    amethasone
    0.64
     Render
    0.63
     rend
    0.62
    Activations Density 0.050%

    No Known Activations