© 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. 34-GEMMASCOPE-RES-131K
    7. 33325
    Prev
    Next
    INDEX
    Explanations

    gunshot wounds

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

    descriptions of physical injuries, particularly gunshot wounds and trauma.

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

    The neuron activates on numeric tokens (i.e., any standalone numbers or digit sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     gegenüber
    -0.79
     OnTrigger
    -0.77
    指甲
    -0.77
     bumpers
    -0.77
     inesperado
    -0.76
    󠁬
    -0.75
    vacy
    -0.75
     أعلام
    -0.72
     agradável
    -0.72
     Bruch
    -0.72
    POSITIVE LOGITS
     wounds
    2.39
     gunshot
    2.30
     wound
    2.25
     Wound
    1.63
    wound
    1.61
     Wounds
    1.53
     bullet
    1.40
    Wound
    1.36
     shot
    1.26
     wounded
    1.21
    Activations Density 0.020%

    No Known Activations