© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 118971
    Prev
    Next
    INDEX
    Explanations

    exacerbation, comorbidity, macromolecular

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

    This neuron detects medical and scientific terminology related to comorbidity, particularly the term "comorbid" and "exacerbation" in medical contexts.

    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
    s
    -4.03
    ים
    -3.03
    轳
    -2.66
    廕
    -2.63
    厯
    -2.59
     แต่
    -2.56
     kumaş
    -2.52
    乆
    -2.48
    vantaged
    -2.47
    řízen
    -2.45
    POSITIVE LOGITS
    in
    3.22
    2
    3.02
    p
    2.88
     và
    2.83
     see
    2.73
     și
    2.67
    ating
    2.66
    1
    2.59
    e
    2.58
    لي
    2.56
    Activations Density 0.730%

    No Known Activations