© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85763
    Prev
    Next
    INDEX
    Explanations

    anorexia nervosa and bulimia

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

    medical terms related to eating disorders, particularly anorexia, bulimia, and body image issues.

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

    The neuron fires on terminology related to eating disorders (e.g., names, symptoms, treatments, and related concepts).

    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
    Recent
    -1.58
    ization
    -1.49
     to
    -1.47
    >
    -1.43
     that
    -1.42
    actéris
    -1.41
    theilung
    -1.37
     the
    -1.30
     Rumors
    -1.27
    _;
    -1.26
    POSITIVE LOGITS
     autre
    1.52
    異なります
    1.35
     भी
    1.35
    Kenapa
    1.31
     desastre
    1.30
     outras
    1.30
    einer
    1.29
    莆
    1.29
    和你
    1.27
    Siapa
    1.27
    Activations Density 0.031%

    No Known Activations