© 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. 104501
    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
     dát
    -1.09
     pneus
    -1.02
    kud
    -0.94
    yit
    -0.94
     prezent
    -0.94
    ឵
    -0.93
     spelen
    -0.91
    andag
    -0.90
    และ
    -0.90
     francês
    -0.90
    POSITIVE LOGITS
     take
    0.97
     although
    0.94
     хотя
    0.93
    ほか
    0.93
     trasparente
    0.93
     mężczyzn
    0.91
    ing
    0.91
    他
    0.90
     where
    0.90
    agregar
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.