© 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. 73499
    Prev
    Next
    INDEX
    Explanations

    license, redistribute or modify

    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
    绿
    -0.86
    green
    -0.77
     zöld
    -0.75
    Green
    -0.73
     metade
    -0.68
    緑
    -0.68
    rense
    -0.68
    donation
    -0.67
     绿
    -0.67
     controlado
    -0.67
    POSITIVE LOGITS
     reduce
    0.77
    wanzig
    0.69
     extre
    0.67
     hatchery
    0.66
    kulu
    0.66
     Lamb
    0.65
     रे
    0.65
     Williams
    0.65
     Amm
    0.64
     Cub
    0.63
    Activations Density 0.045%

    No Known Activations