© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10594
    Prev
    Next
    INDEX
    Explanations

    Medical injury terms

    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_262k_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
     отношениях
    0.46
     भागीदारों
    0.43
    Attk
    0.42
    🛐
    0.40
     বেন
    0.39
    ベーション
    0.39
    資
    0.39
    取引
    0.39
    数を
    0.39
     партне
    0.38
    POSITIVE LOGITS
     injured
    1.09
     injury
    1.08
     injuries
    1.07
    受伤
    0.96
     wounded
    0.91
    injured
    0.90
     Injuries
    0.89
     Injury
    0.88
    伤
    0.87
    Injury
    0.86
    Activations Density 0.085%

    No Known Activations