© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 57747
    Prev
    Next
    INDEX
    Explanations

    Russian verb endings and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    t
    0.56
    ט
    0.54
    은
    0.53
     with
    0.52
    ية
    0.52
    是
    0.50
     as
    0.50
    ።
    0.50
    p
    0.49
    m
    0.49
    POSITIVE LOGITS
     страна
    0.46
     слід
    0.42
     giây
    0.38
    zonych
    0.38
    querysearch
    0.37
    endim
    0.37
     велико
    0.36
     cible
    0.36
     тако
    0.36
     giản
    0.36
    Activations Density 0.000%

    No Known Activations