© 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. 91000
    Prev
    Next
    INDEX
    Explanations

    winning, author, package, players

    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
    Voice
    -0.68
     тен
    -0.67
    setDisable
    -0.66
    nemo
    -0.66
    goon
    -0.64
    당선
    -0.64
    Kate
    -0.63
    antenna
    -0.63
    ér
    -0.63
    KeyType
    -0.62
    POSITIVE LOGITS
     Oliva
    0.80
     mặt
    0.73
     saver
    0.67
     अग
    0.65
     cadre
    0.64
    ndl
    0.63
    ájá
    0.63
     hits
    0.63
    stos
    0.63
     declarar
    0.63
    Activations Density 0.054%

    No Known Activations