© 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. 34-GEMMASCOPE-RES-131K
    7. 116664
    Prev
    Next
    INDEX
    Explanations

    window configuration and display

    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_34/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
    óbal
    -0.81
    יש
    -0.76
    GridQubit
    -0.73
    íso
    -0.72
     pravi
    -0.72
    dza
    -0.72
    cação
    -0.69
    詢
    -0.69
    Barn
    -0.69
     在线
    -0.68
    POSITIVE LOGITS
     title
    0.80
    Decorated
    0.77
    OPS
    0.76
     resolution
    0.75
    setTitle
    0.74
     window
    0.74
     perfiles
    0.73
     Edelman
    0.73
    ofile
    0.73
     icon
    0.73
    Activations Density 0.003%

    No Known Activations