© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 3678
    Prev
    Next
    INDEX
    Explanations

    broad societal concerns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     ایپلی
    0.78
     quãng
    0.76
     esetén
    0.76
    類の
    0.75
     içeren
    0.73
    ه‌ها
    0.73
    ه‌های
    0.72
    ሑ
    0.71
    Company
    0.71
    CATEGORY
    0.71
    POSITIVE LOGITS
    wide
    1.40
     целом
    1.19
     itself
    1.17
    WIDE
    1.14
    全体
    1.12
     entière
    1.09
     മുഴുവ
    1.09
     inteiro
    1.07
    整体
    1.05
    全体の
    1.05
    Activations Density 0.243%

    No Known Activations