© 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. 14429
    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
     kropp
    -1.06
     tylko
    -1.01
     完了
    -0.97
     kroppen
    -0.93
    }}}\
    -0.92
     "-"
    -0.92
    ⠶
    -0.91
    <>();
    -0.91
     they
    -0.91
    ขนาด
    -0.90
    POSITIVE LOGITS
     what
    1.16
     extensive
    1.08
     widespread
    0.99
     appended
    0.97
     plateado
    0.94
     envy
    0.92
     corriendo
    0.92
     cread
    0.91
     specific
    0.90
     पढ़
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.