© 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. 31-GEMMASCOPE-2-RES-262K
    7. 1118
    Prev
    Next
    INDEX
    Explanations

    time units with age or duration

    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/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ₃
    0.30
     целях
    0.30
    ে
    0.30
     περίπτωση
    0.29
    ம்
    0.29
    場合には
    0.29
    ي
    0.29
     UWGM
    0.28
     каждом
    0.28
    י
    0.28
    POSITIVE LOGITS
     consecut
    0.36
     ago
    0.35
     consecutivos
    0.35
     of
    0.33
    充滿
    0.30
    以上的
    0.29
     into
    0.29
     consecutive
    0.29
     boyunca
    0.29
     geleden
    0.29
    Activations Density 0.154%

    No Known Activations