© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54783
    Prev
    Next
    INDEX
    Explanations

    Russian grammatical forms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    Wh
    0.49
    wh
    0.40
    ޢ
    0.38
    Parts
    0.36
     Wh
    0.35
     kär
    0.35
    怀
    0.35
     termos
    0.35
    وڑ
    0.34
    ଢ
    0.34
    POSITIVE LOGITS
     چې
    0.47
    લે
    0.41
     இணைய
    0.40
     देखे
    0.38
    ታት
    0.38
     которой
    0.38
     která
    0.37
     sai
    0.37
    განი
    0.37
    оти
    0.36
    Activations Density 0.002%

    No Known Activations