© 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. 102599
    Prev
    Next
    INDEX
    Explanations

    medical conditions and anatomical parts

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

    medical terminology related to anatomical conditions and abnormalities, particularly focusing on physical disorders and malformations.

    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
    ton
    -1.41
    ra
    -1.37
    le
    -1.33
    mon
    -1.32
    top
    -1.30
    ber
    -1.30
    se
    -1.30
    🤯
    -1.30
    In
    -1.28
    last
    -1.26
    POSITIVE LOGITS
     of
    1.84
     finos
    1.50
     imprimi
    1.50
     cromado
    1.46
     tramit
    1.46
     clás
    1.38
     especí
    1.35
    bumptech
    1.34
    </sup>
    1.29
    elsif
    1.27
    Activations Density 0.285%

    No Known Activations