© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 26765
    Prev
    Next
    INDEX
    Explanations

    foreign language numericals

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    innest
    0.46
     belangrijkste
    0.45
    highest
    0.43
     iyong
    0.42
    to
    0.41
    чность
    0.41
     પોતાની
    0.41
     cittam
    0.41
    籵
    0.40
    <sup>
    0.40
    POSITIVE LOGITS
     excelente
    0.62
     quelconque
    0.61
     solche
    0.59
     autre
    0.57
     altro
    0.57
     determinada
    0.57
     determinado
    0.57
    പക്ഷ
    0.57
     excelentes
    0.56
     solchen
    0.56
    Activations Density 0.008%

    No Known Activations