© 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. 109024
    Prev
    Next
    INDEX
    Explanations

    medical treatment and wounds

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

    content related to medical emergencies, injuries, and treatment of wounded individuals.

    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
    VersionUID
    -0.81
     commerciale
    -0.80
     скан
    -0.78
    Toponymie
    -0.73
     eſt
    -0.73
     distur
    -0.73
     Psic
    -0.73
     Investigators
    -0.72
    まと
    -0.72
     positiva
    -0.72
    POSITIVE LOGITS
     bandage
    1.83
     medical
    1.62
     bandages
    1.60
     band
    1.59
     healing
    1.48
     treatment
    1.41
     wound
    1.40
     Band
    1.33
     bleeding
    1.30
     examined
    1.27
    Activations Density 0.028%

    No Known Activations