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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110608
    Prev
    Next
    INDEX
    Explanations

    Huntington disease

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

    names and references to neurodegenerative disorders, particularly Huntington's disease.

    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_34/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
     Meri
    -0.69
    nx
    -0.69
     駅
    -0.68
     Ong
    -0.68
    rari
    -0.65
    蹣
    -0.65
    icam
    -0.65
     посмотреть
    -0.64
    Tarot
    -0.64
    Stations
    -0.62
    POSITIVE LOGITS
     Huntington
    1.73
     Hunting
    1.44
    Hunt
    1.24
    Hunting
    1.20
     hunting
    1.17
    hung
    1.06
    hunting
    1.06
     Machado
    1.04
     CAG
    1.00
     Hung
    0.97
    Activations Density 0.141%

    No Known Activations