© 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. 10-GEMMASCOPE-RES-131K
    7. 128114
    Prev
    Next
    INDEX
    Explanations

    cytochrome P450

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

    protein and molecule identifiers containing alphanumeric combinations, especially P450 and similar scientific notations.

    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
     —
    -2.53
    ‘
    -2.30
    .
    -2.20
     proporciona
    -2.13
     ‘
    -2.11
     are
    -1.98
    idemia
    -1.97
     głównie
    -1.96
     portray
    -1.95
    :
    -1.92
    POSITIVE LOGITS
     美甲
    2.52
    魮
    2.20
     аккура
    2.19
    쨩
    2.19
     також
    2.16
    १
    2.13
    pergillus
    2.11
     innych
    2.06
    其他的
    2.05
     Also
    2.03
    Activations Density 0.054%

    No Known Activations