© 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. 10-GEMMASCOPE-RES-131K
    7. 47944
    Prev
    Next
    INDEX
    Explanations

    fracture and injury

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

    physical injuries, especially broken bones and sprains.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects mentions of physical injuries or trauma to body parts (e.g. sprains, fractures, dislocations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     duquel
    -1.80
     symboles
    -1.47
     accepter
    -1.45
    踯
    -1.43
    镲
    -1.41
    蚡
    -1.39
     futurs
    -1.38
    鶿
    -1.38
     ؛
    -1.38
     queste
    -1.34
    POSITIVE LOGITS
     as
    1.59
     if
    1.52
     EVERY
    1.45
     nearing
    1.42
     треть
    1.41
     Every
    1.39
     now
    1.38
    لفة
    1.37
     misguided
    1.34
    Every
    1.33
    Activations Density 0.046%

    No Known Activations