© 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. 86117
    Prev
    Next
    INDEX
    Explanations

    clinical examination, symptoms, stages, course

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

    medical terminology related to clinical examinations, findings, or presentations in medical case reports.

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

    The neuron detects clinical case‐report terminology describing patient presentation and examination (e.g. onset, clinical, examination, lesions, papules).

    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
    ícias
    -1.95
    viembre
    -1.89
    omorphisms
    -1.70
    StoryboardSegue
    -1.63
    right
    -1.62
     who
    -1.61
    end
    -1.58
    np
    -1.57
    IL
    -1.52
    kin
    -1.50
    POSITIVE LOGITS
    gucci
    1.58
     hvil
    1.50
    symptoms
    1.41
     fæ
    1.41
    Leírás
    1.40
    gup
    1.38
    ője
    1.38
    unakan
    1.38
    tamaris
    1.38
    டைய
    1.36
    Activations Density 0.242%

    No Known Activations