© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66585
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    GIH
    -0.99
     Sweatshirt
    -0.98
    不开
    -0.93
    ር
    -0.91
    зер
    -0.90
     pandemi
    -0.90
     gabbana
    -0.88
    bedür
    -0.88
    ?><
    -0.88
    ímetro
    -0.87
    POSITIVE LOGITS
     bash
    0.80
    Ана
    0.80
    asants
    0.78
    也會
    0.77
     afuera
    0.77
     konu
    0.75
    Informazioni
    0.72
     themed
    0.72
     to
    0.71
     идёт
    0.71
    Activations Density 0.035%

    No Known Activations