© 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. 128531
    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
    tahu
    -0.97
    ⽤
    -0.91
     الإعلام
    -0.91
     belum
    -0.89
    &=&\
    -0.87
    により
    -0.85
    HttpClientModule
    -0.85
    旆
    -0.85
    Buhari
    -0.84
     ที่
    -0.84
    POSITIVE LOGITS
    There
    1.09
     dégâts
    1.07
    Very
    1.01
     Protects
    1.01
     рік
    0.96
    Identifying
    0.96
    Two
    0.95
    Many
    0.94
     gefeiert
    0.93
    $>
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.