© 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. 10-GEMMASCOPE-RES-131K
    7. 119613
    Prev
    Next
    INDEX
    Explanations

    medical care, conditions, issues

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

    phrases related to medical terminology, healthcare, and treatment contexts.

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

    The neuron activates on mentions of medical or health-related terms (e.g., “medical,” “health,” “medical condition,” 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_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
     of
    -3.14
    '
    -2.94
    ?
    -1.97
     for
    -1.93
     by
    -1.84
            
    -1.75
    呦
    -1.74
     into
    -1.73
     You
    -1.73
     Because
    -1.72
    POSITIVE LOGITS
     envíos
    2.19
     peinados
    1.97
     verdaderos
    1.95
     toallas
    1.94
     bocetos
    1.90
    擽
    1.85
     disfraces
    1.80
     ganadores
    1.80
     lazos
    1.77
     pegatinas
    1.73
    Activations Density 0.033%

    No Known Activations