© 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. 84605
    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
     fabricant
    -1.02
    __);
    -1.02
    ÍS
    -0.93
     contorno
    -0.91
    ▢
    -0.91
    𝕻
    -0.91
    玏
    -0.91
    ITIES
    -0.90
    škai
    -0.90
     priser
    -0.90
    POSITIVE LOGITS
    一层
    1.01
     verbessert
    0.93
     corrects
    0.91
     caters
    0.91
    -$
    0.90
     booze
    0.89
     Gibt
    0.89
     blit
    0.88
     potrebbe
    0.87
     shuffled
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.