© 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. 34993
    Prev
    Next
    INDEX
    Explanations

    Prospective studies involving sepsis

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

    text related to medical or scientific research papers about critical care, intensive care units, and sepsis.

    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
     psoriasis
    -0.79
     גע
    -0.77
     psychologie
    -0.77
     ayudas
    -0.74
    はかなり
    -0.74
     degenerative
    -0.73
     tendremos
    -0.72
     dég
    -0.72
     radioactive
    -0.71
     اجتما
    -0.71
    POSITIVE LOGITS
     ICU
    2.06
    ICU
    1.77
     intensiv
    1.63
     sepsis
    1.60
     bedside
    1.57
     septic
    1.41
    ARDS
    1.37
     critically
    1.29
     hospital
    1.23
     крити
    1.17
    Activations Density 0.535%

    No Known Activations