© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11926
    Prev
    Next
    INDEX
    Explanations

    injuries and wounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🛐
    0.44
    жня
    0.42
     intractable
    0.41
     тай
    0.41
     extermin
    0.40
    窰
    0.40
    ǿ
    0.40
     последнее
    0.39
    匍
    0.39
     эксплуатации
    0.39
    POSITIVE LOGITS
     injuries
    1.08
     injury
    1.03
     wounded
    1.02
     injured
    1.02
    伤
    0.95
     Injuries
    0.92
     Injury
    0.89
    injured
    0.89
     wounds
    0.88
    injury
    0.86
    Activations Density 0.161%

    No Known Activations