© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9415
    Prev
    Next
    INDEX
    Explanations

    fat deposits and content

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

    terminology related to body fat and adipose tissue in scientific or nutritional contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on mentions of “fat” and its close variants (e.g. fatty, adipose) in nutritional or metabolic contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ate
    -2.33
    in
    -2.09
    The
    -2.03
    ian
    -1.85
    ing
    -1.75
    (
    -1.73
     godk
    -1.68
     детьми
    -1.63
    ear
    -1.62
    them
    -1.62
    POSITIVE LOGITS
     It
    1.83
    します
    1.83
     deſt
    1.78
     ถ้า
    1.75
     racconta
    1.73
    trás
    1.73
     When
    1.72
     Cuando
    1.71
     可以
    1.70
     Bedürfn
    1.66
    Activations Density 0.048%

    No Known Activations