© 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-16K
    7. 3174
    Prev
    Next
    INDEX
    Explanations

    approach

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Pudding
    0.69
     Nahrung
    0.67
    intermediates
    0.64
     بٹ
    0.64
    やかに
    0.63
     ഉറ
    0.61
     दिलाया
    0.60
     worries
    0.60
     শুক
    0.59
     꼭
    0.59
    POSITIVE LOGITS
     approach
    4.56
    approach
    4.14
     Approach
    4.13
    Approach
    3.90
     approaches
    3.64
     подход
    3.50
     APPROACH
    3.46
     approche
    3.44
     abordagem
    3.30
     подхода
    3.22
    Activations Density 1.784%

    No Known Activations