© 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. 57388
    Prev
    Next
    INDEX
    Explanations

    fine lines

    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
    Ϳ
    -0.70
    けん
    -0.69
    Canceled
    -0.66
    SWE
    -0.65
    Cancel
    -0.65
    emplace
    -0.64
    cancelled
    -0.64
    чая
    -0.63
    ctile
    -0.63
    case
    -0.63
    POSITIVE LOGITS
    aku
    0.66
     Hales
    0.66
     Schneider
    0.66
    NameExpr
    0.65
    踹
    0.64
    alini
    0.63
     कभी
    0.63
    rogate
    0.62
     Lun
    0.62
    burg
    0.61
    Activations Density 0.076%

    No Known Activations