© 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. 10-GEMMASCOPE-RES-131K
    7. 12925
    Prev
    Next
    INDEX
    Explanations

    Sturgeon Bay spawning roe

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

    words related to fish reproduction, specifically terms like "spawning," "eggs," "roe," and locations like "Bay" where fish may spawn.

    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_10/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
    
    -2.06
    埽
    -2.05
    and
    -2.05
    ato
    -2.02
    OR
    -1.98
    ᠂
    -1.96
    !-
    -1.92
    鼉
    -1.88
     でも
    -1.83
    ном
    -1.82
    POSITIVE LOGITS
     Vermögen
    2.05
     When
    1.90
    ,“
    1.89
    痦
    1.88
     Verhalten
    1.88
    硖
    1.86
     když
    1.85
     zove
    1.85
     Welche
    1.84
    baca
    1.84
    Activations Density 0.004%

    No Known Activations