© 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. 50211
    Prev
    Next
    INDEX
    Explanations

    intestinal tract and disorders

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

    medical terminology related to the gastrointestinal tract.

    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
     LOAD
    -0.78
    너
    -0.78
     Zie
    -0.78
    Insp
    -0.77
    Pener
    -0.75
     McCar
    -0.74
    hauer
    -0.73
    Zie
    -0.72
    눕
    -0.71
    joueur
    -0.71
    POSITIVE LOGITS
     tract
    1.85
     Tract
    1.18
    tract
    1.16
     tracts
    1.13
    TRACT
    1.01
     lumen
    0.97
     mucosa
    0.95
     motility
    0.94
     bleed
    0.88
     perforation
    0.87
    Activations Density 0.078%

    No Known Activations