© 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. 8088
    Prev
    Next
    INDEX
    Explanations

    knee and joints

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

    anatomical terms related to knee joints and associated medical conditions or movements.

    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
    .
    -1.67
     They
    -1.48
     Это
    -1.45
    ꯷
    -1.43
     philosopher
    -1.42
    vimento
    -1.35
     
    -1.34
     it
    -1.33
     полиции
    -1.30
     Literally
    -1.28
    POSITIVE LOGITS
     our
    1.93
    !”
    1.92
     frontière
    1.70
    ⸂
    1.65
    ."<
    1.64
    ?!”
    1.56
    صالات
    1.54
    ());
    1.54
    以上です
    1.52
     quatrième
    1.50
    Activations Density 0.065%

    No Known Activations