© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72283
    Prev
    Next
    INDEX
    Explanations

    enzymes and chemical compounds

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

    technical or scientific terminology related to chemical compounds, enzymes, and biological processes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on longer, multi-syllable content words—especially technical or foreign-derived terms (e.g. compound English or Latin loanwords) appearing in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ’，
    -2.22
    and
    -2.11
    ’
    -1.99
    .’
    -1.82
    ’:
    -1.75
     how
    -1.70
    which
    -1.66
    ’.
    -1.64
    ).
    -1.63
     ‘‘
    -1.63
    POSITIVE LOGITS
    な感じ
    1.88
    $)$
    1.70
    大家都
    1.60
     meisten
    1.58
    ↵↵
    1.57
     You
    1.55
     religión
    1.55
     zprávy
    1.53
     světa
    1.53
    adple
    1.52
    Activations Density 0.001%

    No Known Activations