© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38318
    Prev
    Next
    INDEX
    Explanations

    BIT, 0, 1, Yakov, Endotoxin

    np_acts-logits-general · gemini-2.5-flash-lite

    bitwise operations in programming code, particularly bit definitions and flags.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ﾀ
    -0.99
    nieder
    -0.99
    諫
    -0.97
     createSprite
    -0.96
     consulté
    -0.95
    elesai
    -0.95
     oraz
    -0.92
    請繼續往下閱讀
    -0.92
    ليا
    -0.91
    _{{\
    -0.91
    POSITIVE LOGITS
    ens
    0.93
     hef
    0.92
     detalhe
    0.90
     seules
    0.90
     Brings
    0.90
    descri
    0.89
     Chasse
    0.88
     laço
    0.88
    olutions
    0.88
    rea
    0.88
    Activations Density 0.008%

    No Known Activations