© 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. 55652
    Prev
    Next
    INDEX
    Explanations

    antibiotic prophylaxis and therapy

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

    medical terminology related to antibiotics and pharmaceutical treatments for infections.

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

    The neuron is strongly triggered by specific antibiotic drug names (often multi‐component regimens) and associated clinical treatment terms.

    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
     ويكي
    -0.77
     Medico
    -0.76
    miert
    -0.75
     Marat
    -0.73
     kendaraan
    -0.73
     setDate
    -0.73
     atriz
    -0.73
     corona
    -0.72
    方向
    -0.72
    ueta
    -0.71
    POSITIVE LOGITS
    Gram
    0.87
    floxacin
    0.85
     Gram
    0.85
     empiric
    0.84
     Cultures
    0.82
     stewardship
    0.82
     pare
    0.81
    کتری
    0.78
     Penetration
    0.78
     Infect
    0.78
    Activations Density 0.273%

    No Known Activations