© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162098
    Prev
    Next
    INDEX
    Explanations

    Russian verb endings and prefixes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    c
    1.30
    า
    1.03
    на
    0.94
    Z
    0.94
     \
    0.93
    k
    0.91
    '
    0.89
    פ
    0.83
     approves
    0.82
     Ergebnis
    0.82
    POSITIVE LOGITS
    .{
    0.82
    高
    0.80
    ות
    0.79
    ため
    0.77
     καθώς
    0.77
    のは
    0.77
    нков
    0.75
    ν
    0.75
    ার
    0.75
    па
    0.74
    Activations Density 0.000%

    No Known Activations