© 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. 65934
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms

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

    terms related to professional services and treatments in different fields like healthcare, education, and finance.

    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
    ngdoc
    -0.97
     OFFERS
    -0.90
     these
    -0.89
     ALSO
    -0.88
    側から
    -0.86
     PLUS
    -0.86
    äter
    -0.85
    atás
    -0.84
     Offers
    -0.83
    istet
    -0.83
    POSITIVE LOGITS
     especially
    1.02
     البته
    0.91
    vého
    0.85
     including
    0.85
    ',"
    0.84
     itself
    0.83
    ølge
    0.83
    jména
    0.83
    。"
    0.82
    醯
    0.82
    Activations Density 0.184%

    No Known Activations