© 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. 14691
    Prev
    Next
    INDEX
    Explanations

    symptoms and syndromes

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

    medical condition names and diagnoses, particularly neurological and developmental disorders.

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

    The neuron selectively activates on names of medical conditions, diseases, and syndromes.

    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
    According
    -1.32
    <blockquote>
    -1.28
     ήταν
    -1.27
    姆
    -1.24
    <em>
    -1.23
    te
    -1.22
    瑟
    -1.20
    In
    -1.17
     Glaub
    -1.17
     Eind
    -1.15
    POSITIVE LOGITS
    pośred
    1.49
    祧
    1.41
     Accesorios
    1.38
    皛
    1.37
    obrázek
    1.30
    toolStrip
    1.29
     constitución
    1.27
    鸶
    1.27
    Saiba
    1.27
    licopter
    1.27
    Activations Density 0.096%

    No Known Activations