© 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. 16-GEMMASCOPE-2-RES-262K
    7. 138038
    Prev
    Next
    INDEX
    Explanations

    Acronyms followed by definitions

    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_16_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
    т
    0.71
    ر
    0.66
    ம்
    0.60
    ار
    0.60
    er
    0.59
    م
    0.59
    ت
    0.59
    か
    0.59
    тні
    0.58
    ні
    0.57
    POSITIVE LOGITS
    violence
    0.56
    Violence
    0.54
     bijvoorbeeld
    0.51
     violência
    0.51
    новых
    0.49
     შემთხვევაში
    0.49
     например
    0.49
    డ్‌
    0.48
     violently
    0.48
     برطانیہ
    0.48
    Activations Density 0.110%

    No Known Activations