© 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. 62391
    Prev
    Next
    INDEX
    Explanations

    Polish and Russian abstract nouns and verb endings

    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
    ak
    1.26
    ia
    1.09
    it
    1.06
    ons
    1.05
    ani
    1.04
    ist
    1.02
    are
    1.02
    도
    1.02
    io
    0.99
    her
    0.98
    POSITIVE LOGITS
    \
    1.03
     reorgan
    1.02
     subdue
    1.02
     дости
    1.01
    ем
    0.99
     powied
    0.98
     toán
    0.96
     thúc
    0.95
     gên
    0.91
     générales
    0.90
    Activations Density 0.001%

    No Known Activations