© 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. 42101
    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
    𝗬
    -0.95
    ırım
    -0.93
     城市
    -0.89
    ";
    -0.88
    だって
    -0.87
     vérifier
    -0.87
    ânt
    -0.87
    зировать
    -0.87
    ouc
    -0.86
     venice
    -0.86
    POSITIVE LOGITS
    0
    1.00
     small
    0.95
     large
    0.94
    浔
    0.93
     when
    0.93
     so
    0.90
     continued
    0.89
     balcón
    0.89
     white
    0.87
    kket
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.