© 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. 99188
    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
     bestens
    -1.00
     sicheren
    -0.98
     vielfäl
    -0.98
    安く
    -0.93
    qb
    -0.89
    迫力
    -0.88
     этого
    -0.87
    FML
    -0.87
    骡
    -0.86
    Done
    -0.85
    POSITIVE LOGITS
     pequ
    1.14
     Verf
    1.00
     gelt
    0.96
     hellen
    0.96
     remedio
    0.95
    ⊔
    0.95
    fillText
    0.94
     Leurs
    0.93
    </thead>
    0.93
     applications
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.