© 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. 75457
    Prev
    Next
    INDEX
    Explanations

    hospital admissions, patients, staff

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

    terms related to hospitals, healthcare facilities, and hospital-acquired infections.

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

    The neuron strongly activates on mentions of “hospital” (and related compounds like hospital‐associated, hospital‐acquired, nosocomial) in the text.

    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
    桫
    -1.83
    鸶
    -1.81
    ⚣
    -1.72
    赑
    -1.69
     importants
    -1.64
     dangere
    -1.63
    𓆏
    -1.61
    旁边的
    -1.60
     tè
    -1.59
    苼
    -1.58
    POSITIVE LOGITS
     as
    2.11
    in
    1.97
     where
    1.95
     when
    1.79
    la
    1.73
    c
    1.62
     simply
    1.61
     stemming
    1.60
     our
    1.59
     indicating
    1.58
    Activations Density 0.081%

    No Known Activations