© 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. 91385
    Prev
    Next
    INDEX
    Explanations

    trauma and fractures

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

    medical terms related to bone fractures and injuries.

    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
     cáncer
    -0.92
    żna
    -0.78
     malattia
    -0.76
     CANCER
    -0.75
    himo
    -0.75
     edición
    -0.72
    偈
    -0.72
    çoivent
    -0.72
    尾巴
    -0.71
     Abfall
    -0.71
    POSITIVE LOGITS
     trauma
    1.30
     fractures
    1.22
     contu
    1.07
     fracture
    1.05
     traumatic
    1.04
     crush
    0.96
     injury
    0.96
     closed
    0.95
     mechanism
    0.93
     lacer
    0.93
    Activations Density 0.227%

    No Known Activations