© 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. 1366
    Prev
    Next
    INDEX
    Explanations

    medical artery terms

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

    anatomical terms related to arteries in medical contexts.

    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
     "
    -3.94
    "
    -3.02
    )
    -3.02
     '
    -2.95
     is
    -2.84
     
    -2.81
    C
    -2.78
    J
    -2.77
    al
    -2.73
    This
    -2.67
    POSITIVE LOGITS
     работал
    2.56
     pietre
    2.48
    睒
    2.47
     ceramica
    2.45
     criou
    2.42
    餍
    2.41
     NACIONAL
    2.38
     sklo
    2.36
    €,
    2.34
    tamaris
    2.34
    Activations Density 0.008%

    No Known Activations