© 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. 44976
    Prev
    Next
    INDEX
    Explanations

    medical descriptions of extremities

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

    medical terms specifically referring to extremities or limbs of the body.

    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
    </i>
    -2.95
    鲠
    -2.44
     THEM
    -2.31
    -
    -2.28
     stalwart
    -2.22
    e
    -2.22
    such
    -2.11
    </b>
    -2.11
    </h1>
    -2.06
    with
    -2.06
    POSITIVE LOGITS
    酲
    3.20
    
    3.03
    觏
    2.98
     शुर
    2.86
    ญี่ป
    2.55
    
    2.52
    ୌ
    2.50
    瑧
    2.45
    汭
    2.45
     ſame
    2.44
    Activations Density 0.003%

    No Known Activations