© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99918
    Prev
    Next
    INDEX
    Explanations

    patient encounters

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

    XML and code formatting elements in technical documents.

    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
    bus
    -0.86
     Monat
    -0.75
    usk
    -0.75
     Buyers
    -0.74
    copyOf
    -0.71
    rän
    -0.71
    cosal
    -0.70
     QUIZ
    -0.69
    AGM
    -0.69
    зни
    -0.68
    POSITIVE LOGITS
     patient
    1.52
     patients
    1.38
     inpatient
    1.33
     encounters
    1.27
     encounter
    1.27
    encounter
    1.23
     Patient
    1.18
     visit
    1.14
     Encounter
    1.13
     outpatient
    1.13
    Activations Density 0.009%

    No Known Activations