© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82717
    Prev
    Next
    INDEX
    Explanations

    punitive tariff

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptions and categorizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ج
    0.50
    的工作
    0.44
    reload
    0.43
    кта
    0.41
    ع
    0.41
     زیبا
    0.41
    ↵
    0.40
    但在
    0.40
     tabindex
    0.40
    ंग
    0.40
    POSITIVE LOGITS
     vode
    0.53
     caratteristiche
    0.52
     saranno
    0.49
     differs
    0.48
     sarà
    0.47
     alcuni
    0.47
     dois
    0.47
     sarebbe
    0.46
     ಎರಡು
    0.46
     altra
    0.46
    Activations Density 0.000%

    No Known Activations