© 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. 65935
    Prev
    Next
    INDEX
    Explanations

    disease, neurological conditions, susceptibility

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

    This neuron identifies medical and disease-related terms, particularly focusing on neurological conditions, cancers, and chronic diseases.

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

    The neuron specializes in spotting biomedical pathology terms—especially disease names and lesion‐ or demyelination‐related words.

    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
    ︲
    -1.98
     vetores
    -1.80
     วัน
    -1.77
     Sekarang
    -1.76
    𓁹
    -1.66
     černé
    -1.63
    WAUKEE
    -1.60
    ネジ
    -1.56
    
    -1.55
     zařízení
    -1.53
    POSITIVE LOGITS
     through
    2.30
     with
    1.93
     different
    1.89
     from
    1.86
     without
    1.84
     despite
    1.70
     by
    1.67
     specific
    1.63
     one
    1.54
     even
    1.52
    Activations Density 2.054%

    No Known Activations