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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82695
    Prev
    Next
    INDEX
    Explanations

    gastrointestinal diseases and treatments

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

    This neuron detects content related to gastrointestinal and digestive system medical terminology.

    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
     qubit
    -0.93
     تب
    -0.83
     نقاشی
    -0.83
     leukemia
    -0.82
     Mening
    -0.82
     insecticide
    -0.81
    との
    -0.80
     hypotension
    -0.80
    肾
    -0.79
     melanoma
    -0.79
    POSITIVE LOGITS
     intestinal
    2.30
     Gastroenter
    2.11
     gastro
    2.03
     gut
    1.98
     Gastro
    1.96
    Gastro
    1.92
    intestinal
    1.88
     stomach
    1.88
     gastroenter
    1.83
     digestive
    1.82
    Activations Density 0.632%

    No Known Activations