© 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. 22-GEMMASCOPE-RES-131K
    7. 130225
    Prev
    Next
    INDEX
    Explanations

    The neuron detects mentions of specific diseases or medical conditions (e.g., “coronary heart disease,” “Hodgkin lymphoma”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    autism spectrum disorder

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

    medical and anatomical terms in scientific or clinical 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_22/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
     what
    -0.98
    ignment
    -0.96
     (!__
    -0.96
     ersetzt
    -0.90
    kan
    -0.90
    kz
    -0.90
    ng
    -0.90
    WHAT
    -0.88
     both
    -0.85
    達が
    -0.84
    POSITIVE LOGITS
     (
    1.23
     أكثر
    0.98
    érique
    0.94
    Здра
    0.91
     demostr
    0.90
    isei
    0.87
     grafting
    0.86
    crisy
    0.85
    aları
    0.85
     même
    0.84
    Activations Density 1.144%

    No Known Activations