© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64407
    Prev
    Next
    INDEX
    Explanations

    emergency room or department

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

    medical or health-related emergency situations occurring in hospital emergency rooms.

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

    The neuron fires on chunks of text that look like academic section headings—especially titles and numbered subtitles in study reports (e.g. paper titles, “Related Injuries…,” “From 2001 to 2014,” journal‐style headings).

    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
    任
    -0.83
     مكتب
    -0.81
    них
    -0.79
     任
    -0.79
    さっぱり
    -0.78
    就會
    -0.78
    Oxygen
    -0.78
     Leche
    -0.76
    ophora
    -0.74
     菊
    -0.74
    POSITIVE LOGITS
     emergency
    2.52
     ER
    2.17
     Emergency
    2.14
    emergency
    1.88
    Emergency
    1.82
     ED
    1.40
     department
    1.38
     Urgent
    1.34
     urgent
    1.34
     EMERGENCY
    1.31
    Activations Density 0.062%

    No Known Activations