© 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. 10-GEMMASCOPE-RES-131K
    7. 19763
    Prev
    Next
    INDEX
    Explanations

    ileum and related medical terms

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

    the word "ile" followed by letters that form medical terminology related to intestinal anatomy.

    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_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
    
    -2.45
     rekan
    -1.95
     OGSÅ
    -1.93
    ↵↵
    -1.91
    钨
    -1.89
     geschreven
    -1.88
     је
    -1.87
     relies
    -1.86
     kült
    -1.86
    的核心
    -1.85
    POSITIVE LOGITS
    This
    2.61
    stood
    2.56
    It
    2.55
    他
    2.47
    ers
    2.42
     gefährlich
    2.23
    the
    2.23
    ll
    2.19
    8
    2.17
     Moreover
    2.16
    Activations Density 0.001%

    No Known Activations