© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9979
    Prev
    Next
    INDEX
    Explanations

    heart and cardiac conditions

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

    medical terms related to the heart and cardiac conditions.

    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
     of
    -1.66
    .”
    -1.54
    tshell
    -1.37
     максимально
    -1.34
    usitis
    -1.33
    了自己
    -1.33
     novidades
    -1.32
    菓
    -1.32
     to
    -1.29
    issors
    -1.29
    POSITIVE LOGITS
    1.89
    ↵↵
    1.72
    Heart
    1.69
     and
    1.47
    ۵
    1.45
    一旁
    1.44
    现在
    1.38
    dapat
    1.36
     heart
    1.35
    mouseup
    1.34
    Activations Density 0.167%

    No Known Activations