© 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. 40-GEMMASCOPE-2-RES-262K
    7. 12936
    Prev
    Next
    INDEX
    Explanations

    past tense verbal suffixes

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     করতাম
    0.45
    гура
    0.41
    𝐾
    0.41
    ূতন
    0.40
    годні
    0.40
    филь
    0.40
     المصفوفه
    0.40
     अहिले
    0.40
     المعادلات
    0.39
     কৰি
    0.39
    POSITIVE LOGITS
     છે
    0.66
     है
    0.64
     ہے
    0.61
     था
    0.53
    ছে
    0.52
     थी
    0.49
    る
    0.48
     हैं
    0.47
    ।
    0.47
     আছে
    0.46
    Activations Density 0.003%

    No Known Activations