© 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. 673
    Prev
    Next
    INDEX
    Explanations

    injury and trauma

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

    text related to injuries, accidents, and medical trauma.

    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
     halben
    -0.78
     مرگ
    -0.77
    ーカー
    -0.76
    ifan
    -0.75
    リズム
    -0.74
     desemple
    -0.71
    Madness
    -0.71
    heiros
    -0.70
    textLabel
    -0.69
    ighborhood
    -0.69
    POSITIVE LOGITS
     injury
    5.72
     injuries
    5.41
     injured
    4.78
     Injury
    4.50
    injury
    4.28
     Injuries
    4.22
     injure
    3.97
    Injury
    3.75
    injured
    3.69
    Injuries
    3.61
    Activations Density 0.179%

    No Known Activations