© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72037
    Prev
    Next
    INDEX
    Explanations

    Oxidative stress

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

    numbers and statistics in sports contexts, particularly in hockey and other professional sports.

    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
     kabel
    -0.85
    ignen
    -0.82
     koning
    -0.79
    çi
    -0.78
    ANCING
    -0.78
    вето
    -0.76
    bánh
    -0.76
    фон
    -0.76
     active
    -0.75
    ioc
    -0.75
    POSITIVE LOGITS
    报警
    0.87
    謠
    0.84
    istible
    0.83
    我會
    0.82
    這樣的
    0.82
    mishes
    0.82
    yente
    0.82
    へ向
    0.82
     उस
    0.81
     ajang
    0.81
    Activations Density 0.001%

    No Known Activations