© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67256
    Prev
    Next
    INDEX
    Explanations

    obesity and overweight

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

    words and concepts related to obesity, overweight, and weight-related health issues.

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

    The neuron primarily activates on words and phrases referring to excess body weight or obesity (e.g., “weight,” “overweight,” “obese,” “obesity”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ol
    -1.09
    in
    -1.07
    ia
    -1.05
    on
    -1.05
    )$
    -1.00
    ネート
    -1.00
     to
    -0.99
    at
    -0.98
    谟
    -0.98
    um
    -0.97
    POSITIVE LOGITS
     weight
    1.40
     Obesity
    1.39
     obesity
    1.39
    kond
    1.25
    berat
    1.23
     Weight
    1.20
    Obesity
    1.20
    rakt
    1.20
     adipose
    1.16
     desbloquear
    1.16
    Activations Density 0.094%

    No Known Activations