© 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. 102736
    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
    covite
    -1.05
     Blogs
    -0.98
    AKAN
    -0.96
    ciutto
    -0.95
    plotlib
    -0.95
     next
    -0.92
    ussia
    -0.91
    rotter
    -0.90
    bbat
    -0.90
    akan
    -0.88
    POSITIVE LOGITS
     största
    0.95
    Mål
    0.94
    白い
    0.92
     Erkrankungen
    0.92
     Solis
    0.90
    ادامه
    0.87
     мамы
    0.86
    نتیجه
    0.86
    مرحله
    0.85
    One
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.