© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123629
    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
    0
    -1.95
     to
    -1.88
     ก็
    -1.87
     подобрать
    -1.81
    なので
    -1.75
     otros
    -1.71
    ですので
    -1.66
     
    -1.66
    He
    -1.63
     Aucune
    -1.62
    POSITIVE LOGITS
    tól
    2.39
    ранее
    2.16
    ers
    2.11
    penuhi
    2.11
    獼
    2.03
    ziale
    2.03
    ᯅ
    2.00
     transfé
    1.95
    alties
    1.94
    ні
    1.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.