© 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. 128697
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ҽ
    -1.06
    Pome
    -0.93
    mantec
    -0.92
     Línea
    -0.91
    Gost
    -0.91
    VHS
    -0.90
     tabak
    -0.89
     tromper
    -0.88
    Kapp
    -0.88
    centerX
    -0.86
    POSITIVE LOGITS
    being
    1.06
     being
    0.95
    ARE
    0.90
    %),
    0.90
    kowej
    0.88
    닥
    0.85
     makeStyles
    0.85
     asistir
    0.84
    ੱਚ
    0.84
    歩いて
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.