© 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. 10-GEMMASCOPE-RES-131K
    7. 7767
    Prev
    Next
    INDEX
    Explanations

    technology

    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_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
    说到
    -1.43
    cookieParser
    -1.38
    kadot
    -1.34
    については
    -1.27
    ⤥
    -1.26
    TestingModule
    -1.26
    eynman
    -1.25
    记得
    -1.23
     /\.(
    -1.23
     querían
    -1.23
    POSITIVE LOGITS
    Think
    1.48
     simplicité
    1.38
    Find
    1.36
    よな
    1.36
     perfected
    1.34
    Want
    1.33
    from
    1.31
    寕
    1.30
     geringen
    1.30
    But
    1.30
    Activations Density 0.029%

    No Known Activations