© 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. 85273
    Prev
    Next
    INDEX
    Explanations

    medical and biological substances

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

    scientific and medical terminology related to diseases, biological entities, and chemical compounds.

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

    This neuron responds to highly specific technical or scientific entity names and terms—such as species epithets, biochemical compounds, disease names, pharmaceutical ingredients, or database/table identifiers.

    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
     for
    -1.88
     about
    -1.61
     what
    -1.38
     zoals
    -1.30
    fordshire
    -1.29
    titian
    -1.27
    ].[
    -1.27
     "";
    -1.23
    …~
    -1.23
    4
    -1.22
    POSITIVE LOGITS
     you
    1.73
     Erschein
    1.41
    紅色
    1.41
    ſſes
    1.39
    大人気
    1.37
    皆さま
    1.35
    红色的
    1.34
     Aussehen
    1.34
     Fähigkeit
    1.33
     sustancias
    1.31
    Activations Density 0.173%

    No Known Activations