© 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. 22-GEMMASCOPE-RES-131K
    7. 25856
    Prev
    Next
    INDEX
    Explanations

    medical treatments and conditions

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

    medical and scientific terminology related to treatments, procedures, and biological structures.

    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_22/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
    ut
    -1.28
     créées
    -1.27
    Doesn
    -1.26
     viennent
    -1.23
     подойдет
    -1.21
    ėjimo
    -1.20
    ského
    -1.17
    為に
    -1.17
    ской
    -1.16
    ｃｍ
    -1.16
    POSITIVE LOGITS
     can
    2.36
     is
    1.75
     could
    1.70
     often
    1.66
     may
    1.63
     usually
    1.55
     are
    1.50
     also
    1.42
     často
    1.25
    があり
    1.23
    Activations Density 0.537%

    No Known Activations