© 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. 112208
    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
    něž
    -0.96
    ました
    -0.95
     Inventories
    -0.93
     Aims
    -0.89
     Amu
    -0.89
    mall
    -0.88
     Tasks
    -0.88
    rawn
    -0.87
    bis
    -0.86
    morphic
    -0.86
    POSITIVE LOGITS
     Cuando
    1.11
     cuando
    0.97
     quando
    0.96
     nawet
    0.94
     Berücksich
    0.93
    𔘓
    0.92
    {}/
    0.92
     این
    0.91
    已经
    0.89
     Когда
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.