© 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. 59572
    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
     shining
    -0.89
     njia
    -0.88
     frutos
    -0.86
     fortalec
    -0.85
    ↵↵
    -0.84
     ...
    -0.82
     farklı
    -0.81
    ůž
    -0.81
     Вот
    -0.81
    unpublished
    -0.81
    POSITIVE LOGITS
     perle
    0.97
     Polyester
    0.97
    istet
    0.95
     vinyle
    0.94
     PROBLE
    0.93
     перио
    0.92
     Vitamina
    0.91
     raja
    0.91
     bahagia
    0.91
    ꯖ
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.