© 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. 127658
    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
    轳
    -0.96
    很好的
    -0.90
    平民
    -0.87
    ッと
    -0.86
    organe
    -0.83
    Boletín
    -0.80
    fiant
    -0.79
    魑
    -0.79
     tiempos
    -0.78
     quién
    -0.78
    POSITIVE LOGITS
    ària
    0.95
     Bick
    0.93
    continence
    0.93
     unaweza
    0.88
     경우
    0.87
     uly
    0.87
    herent
    0.86
    cação
    0.86
     Qaraldi
    0.86
    還可以
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.