© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41178
    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
     sew
    -0.94
    Side
    -0.91
     Side
    -0.90
     dari
    -0.85
     .
    -0.84
     Cela
    -0.84
    </th>
    -0.82
    ء
    -0.82
    ネイル
    -0.81
     город
    -0.81
    POSITIVE LOGITS
    fabulous
    1.03
    ☺
    1.02
     digitale
    1.02
    tığı
    1.00
     taas
    0.99
    骝
    0.96
     kyt
    0.96
    维基
    0.96
     素人
    0.95
     maksi
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.