© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63207
    Prev
    Next
    INDEX
    Explanations

    nosocomial infections or nitric oxide synthase

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

    The neuron detects the term "nosocomial" (hospital-acquired infections) and its variations in medical texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    incón
    -0.77
    衊
    -0.75
     простой
    -0.73
    paedia
    -0.73
     Ordens
    -0.71
    ación
    -0.71
    賽
    -0.71
     gustó
    -0.71
    coque
    -0.70
    tapi
    -0.70
    POSITIVE LOGITS
     Nos
    1.09
    Nos
    1.04
     nos
    0.98
     Nose
    0.88
    bleed
    0.88
    erunner
    0.80
    Nose
    0.77
    dive
    0.77
     NOS
    0.76
     sms
    0.75
    Activations Density 0.016%

    No Known Activations