© 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. 22-GEMMASCOPE-2-RES-262K
    7. 10814
    Prev
    Next
    INDEX
    Explanations

    relationship or action following words

    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_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    translated
    0.80
    ဖြေ
    0.80
     формування
    0.80
    woven
    0.78
     எப்போதும்
    0.74
    ně
    0.73
     развитие
    0.70
    organized
    0.69
    仕事
    0.69
    )\}$
    0.69
    POSITIVE LOGITS
     into
    2.02
    Into
    1.55
     using
    1.54
     Into
    1.52
    into
    1.50
     onto
    1.40
     INTO
    1.38
     باستخدام
    1.32
     इनटू
    1.31
     bằng
    1.25
    Activations Density 0.367%

    No Known Activations