© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 5510
    Prev
    Next
    INDEX
    Explanations

    injury and injured people

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

    physical injury or wounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibaba
    0.39
    取締
    0.38
    冚
    0.38
    🔒
    0.38
     پیس
    0.38
    >=</
    0.36
    取引
    0.36
    監査
    0.36
    諦
    0.36
     వ్యవ
    0.36
    POSITIVE LOGITS
     injuries
    4.00
     injury
    3.84
     Injuries
    3.78
     injured
    3.70
     Injury
    3.63
     injure
    3.53
    Injury
    3.52
    injury
    3.50
    伤
    3.48
    受伤
    3.39
    Activations Density 0.298%

    No Known Activations