© 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. 10432
    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
    paravant
    -0.97
     participé
    -0.92
     复古
    -0.91
     Russland
    -0.91
    ωση
    -0.91
    taway
    -0.91
    橚
    -0.90
     we
    -0.90
    部分が
    -0.90
    zhang
    -0.89
    POSITIVE LOGITS
    Neder
    1.02
    汩
    0.94
     Estates
    0.93
    िल्म
    0.92
     GetEnumerator
    0.91
     kirj
    0.89
     unbekannt
    0.88
    oproject
    0.88
     ❤️
    0.87
     не
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.