© 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. 111802
    Prev
    Next
    INDEX
    Explanations

    cofounder or cofactor

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

    the word "cofactor" or variations like "cofactors" in scientific texts.

    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
    .
    -2.73
    '
    -2.70
     bedeut
    -2.59
     \
    -2.55
    "
    -2.45
     he
    -2.42
     $
    -2.41
    ),
    -2.36
     .
    -2.36
     Nachmittag
    -2.28
    POSITIVE LOGITS
    媖
    3.48
    錞
    3.16
    ’，
    3.14
    ’
    2.95
    ⦊
    2.86
    卨
    2.73
    ाउनलोड
    2.70
    chtenstein
    2.48
    釹
    2.47
     土産
    2.44
    Activations Density 0.003%

    No Known Activations