© 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. 100226
    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
     Instead
    -1.03
     of
    -0.90
    畔
    -0.89
    Occasionally
    -0.87
    mètres
    -0.87
    '>
    -0.87
     vedno
    -0.86
    谎
    -0.85
     Роз
    -0.85
     Meanwhile
    -0.85
    POSITIVE LOGITS
     preservation
    0.92
    ectl
    0.90
     cuchar
    0.86
     mileage
    0.85
    guous
    0.85
    tedì
    0.84
     preserving
    0.84
    えば
    0.84
     cumplen
    0.84
     extracting
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.