© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 25893
    Prev
    Next
    INDEX
    Explanations

    epidemiology and morphology studies

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

    The neuron activates for scientific terminology related to the study of characteristics and distributions, particularly "epidemiology" and "morphology."

    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
     Of
    -2.83
    Of
    -2.52
    ?"
    -2.47
    </i>
    -2.31
     was
    -2.30
     However
    -2.20
    !"
    -2.16
    有意
    -2.14
     They
    -2.14
     are
    -2.14
    POSITIVE LOGITS
    .
    3.25
     of
    3.02
     белом
    2.53
     geringen
    2.27
     серебри
    2.25
    薮
    2.25
     Septiembre
    2.19
    ”]
    2.17
     участке
    2.17
     ярко
    2.16
    Activations Density 0.111%

    No Known Activations