© 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. 22-GEMMASCOPE-RES-131K
    4. 39558
    Prev
    Next
    INDEX
    Explanations

    unexplained chronic illness

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

    descriptions of medical symptoms and chronic health conditions, particularly unexplained or persistent symptoms.

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

    The neuron activates on technical medical terminology, especially names or descriptions of diseases, symptoms, and clinical conditions.

    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
    um
    -0.98
     while
    -0.98
    ile
    -0.96
     inevitable
    -0.96
     возрасте
    -0.94
    ther
    -0.91
    size
    -0.89
    hile
    -0.89
     monumental
    -0.89
    bus
    -0.88
    POSITIVE LOGITS
     unsolved
    1.16
    CUIT
    1.02
     ujednoznacz
    1.02
    ⇑
    1.02
     unexplained
    1.00
     समस्या
    0.98
     mystérie
    0.98
     Países
    0.97
    jména
    0.97
    ปัญหา
    0.96
    Activations Density 0.256%

    No Known Activations