© 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. 115882
    Prev
    Next
    INDEX
    Explanations

    diabetes complications

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

    text discussing medical complications, risks, or side effects of diseases or conditions.

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

    The neuron fires on technical biomedical terms describing disease processes, complications, and management.

    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
    циа
    -0.81
    幸运
    -0.79
    Симпто
    -0.78
     valide
    -0.76
    鍮
    -0.75
    棋
    -0.73
    ссажи
    -0.73
     sobs
    -0.73
     良
    -0.72
     Gastroenter
    -0.72
    POSITIVE LOGITS
     complications
    5.66
     complication
    4.69
     Complications
    4.47
    Complications
    3.92
     complicaciones
    3.13
     complica
    2.83
     complic
    2.44
     complicate
    2.33
    слож
    2.03
     komp
    1.95
    Activations Density 0.222%

    No Known Activations