© 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. 128861
    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
    The
    -1.17
    www
    -1.12
    e
    -1.11
    你也
    -1.09
    ATTACH
    -1.02
    new
    -1.02
    你不要
    -1.00
     нагрузки
    -0.96
     обеспечение
    -0.94
    事も
    -0.93
    POSITIVE LOGITS
    polite
    1.02
    kapital
    1.02
     to
    0.96
    }`
    0.96
     gedachten
    0.94
    西哥
    0.92
    slider
    0.91
    हर
    0.91
     Cinematic
    0.90
    ？”
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.