© 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. 59052
    Prev
    Next
    INDEX
    Explanations

    diseases involving inflammation

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

    names of medical conditions and diseases.

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

    The neuron activates on mentions of specific biomedical disease or syndrome names (e.g. “Behçet’s disease,” “Kawasaki syndrome,” “sarcoidosis,” etc.).

    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
     rekomendasi
    -0.81
    LTC
    -0.75
    돌
    -0.71
     Branca
    -0.67
     Verne
    -0.66
     outstretched
    -0.66
    ولوج
    -0.65
    ब्
    -0.65
    doub
    -0.65
    \]
    -0.64
    POSITIVE LOGITS
     inflammation
    1.24
     Inflammation
    1.07
     flares
    1.07
     inflama
    1.05
    inflammation
    0.98
    inflammatory
    0.96
     flare
    0.94
     Kawasaki
    0.94
    orti
    0.91
     inflammatory
    0.91
    Activations Density 0.222%

    No Known Activations