© 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. 21312
    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
     '*')
    -0.96
     in
    -0.93
     then
    -0.91
    lowed
    -0.91
    lamó
    -0.89
    mindedness
    -0.89
    켰
    -0.89
    cohol
    -0.88
     it
    -0.87
    isable
    -0.87
    POSITIVE LOGITS
    ↵
    1.16
     testar
    1.05
     unserer
    0.95
     haute
    0.90
     provar
    0.88
     handover
    0.88
     propuesta
    0.88
    ните
    0.87
     appréci
    0.86
     photoshoot
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.