© 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. 78222
    Prev
    Next
    INDEX
    Explanations

    acute medical conditions

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

    medical conditions that start with "acute" 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
     alcuni
    -0.95
     alcune
    -0.91
     juiz
    -0.88
     irmão
    -0.88
     adhering
    -0.88
     freio
    -0.87
     braço
    -0.87
     Reihenfolge
    -0.87
    REQU
    -0.86
     pregi
    -0.85
    POSITIVE LOGITS
     Acute
    1.47
    Acute
    1.46
     acute
    1.36
    acute
    1.16
     phase
    1.08
    📐
    1.01
    ższe
    1.01
     angle
    0.96
     abdomen
    0.95
     kidney
    0.94
    Activations Density 0.059%

    No Known Activations