© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 143693
    Prev
    Next
    INDEX
    Explanations

    deserves quality

    np_acts-logits-general · gemini-2.5-flash-lite

    pending action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clarkson
    0.57
     Coates
    0.57
     Tew
    0.56
     男
    0.56
     Beckham
    0.55
     Ellison
    0.55
     Pochettino
    0.54
     Lipschitz
    0.54
     Loại
    0.54
     `:`,
    0.54
    POSITIVE LOGITS
    jar
    0.46
    Trusted
    0.46
    Title
    0.45
    TIL
    0.44
    Commands
    0.44
    چہ
    0.42
    Keeper
    0.42
    Promise
    0.42
    Color
    0.42
    Rotation
    0.42
    Activations Density 0.000%

    No Known Activations