© 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. 65457
    Prev
    Next
    INDEX
    Explanations

    at first

    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_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
     for
    -1.85
     in
    -1.70
     from
    -1.66
     the
    -1.66
     since
    -1.65
     if
    -1.60
     facilitates
    -1.56
    {
    -1.52
     an
    -1.48
     other
    -1.46
    POSITIVE LOGITS
     Dinas
    1.73
    轳
    1.71
     jednej
    1.62
    ⑊
    1.59
     gmina
    1.59
     aislados
    1.58
     多少
    1.55
     konfigura
    1.53
     atrak
    1.52
    
    1.49
    Activations Density 0.062%

    No Known Activations