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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21150
    Prev
    Next
    INDEX
    Explanations

    arthralgia, arthroscopic, Arthropoda

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

    medical terms related to joint conditions, particularly with the prefix "arth-" as in arthritis, arthroscopy, and arthralgia.

    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
    s
    -5.25
    ’
    -3.09
    ین
    -3.02
    ی
    -3.00
    .”
    -2.83
    ’，
    -2.50
    厛
    -2.50
    We
    -2.50
     クリア
    -2.47
     pepe
    -2.44
    POSITIVE LOGITS
     Would
    2.81
     soothe
    2.77
     You
    2.70
     certaines
    2.63
     Should
    2.58
     упаковка
    2.58
     savor
    2.56
     neutralize
    2.53
     enlightening
    2.52
     Personally
    2.50
    Activations Density 0.010%

    No Known Activations