© 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. 34-GEMMASCOPE-RES-131K
    7. 60382
    Prev
    Next
    INDEX
    Explanations

    complementary and alternative medicine

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

    references to complementary and alternative medicine (CAM) in medical or healthcare contexts.

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

    The neuron strongly activates on mentions of complementary and alternative medicine (CAM) or related umbrella terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    诊断
    -0.77
    roth
    -0.71
     liquor
    -0.69
     Addis
    -0.68
     orthopedic
    -0.67
    ahead
    -0.67
    alyse
    -0.67
    isert
    -0.66
    ല്‍
    -0.66
    jackson
    -0.66
    POSITIVE LOGITS
     complementary
    2.31
     Complementary
    2.22
     alternative
    1.55
     complimentary
    1.49
     CAM
    1.46
     Complimentary
    1.45
     integrative
    1.39
     Alternative
    1.37
    Comple
    1.35
    Alternative
    1.30
    Activations Density 0.063%

    No Known Activations