© 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. 113056
    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
     científicas
    -0.94
    '
    -0.94
    an
    -0.93
    落とし
    -0.84
     Products
    -0.83
     drei
    -0.83
     deportivas
    -0.83
     junge
    -0.82
     
    -0.82
     Records
    -0.82
    POSITIVE LOGITS
    Categoría
    1.10
    eado
    1.09
    litis
    1.08
    ולוג
    1.07
    aide
    1.06
    愎
    1.06
    hasa
    1.05
    Rptr
    1.04
     梨
    1.04
     >
    1.03
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.