© 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. 8780
    Prev
    Next
    INDEX
    Explanations

    tread patterns and life

    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
    f
    0.72
    c
    0.68
    ק
    0.62
    v
    0.59
     LCA
    0.58
    im
    0.57
    vā
    0.56
     проекта
    0.54
    a
    0.54
    ک
    0.54
    POSITIVE LOGITS
    ]=
    0.60
     দুর
    0.51
     Вікіпедії
    0.50
     tread
    0.49
     FontFamily
    0.49
     രംഗ
    0.48
    ๊ก
    0.48
     联系
    0.48
    မျ
    0.47
     Leben
    0.47
    Activations Density 0.003%

    No Known Activations