© 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. 108556
    Prev
    Next
    INDEX
    Explanations

    Japanese verb conjugations and 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
    ۰
    1.25
    。
    1.23
    น
    1.22
    '
    1.19
    '।
    1.16
    ۹
    1.15
    iš
    1.13
    。,
    1.10
    ג
    1.07
    ).
    1.06
    POSITIVE LOGITS
    2
    1.68
     and
    1.17
     or
    1.12
    able
    1.12
    ra
    1.09
    4
    1.08
    on
    1.05
    3
    1.02
    ris
    1.02
    icious
    1.02
    Activations Density 0.000%

    No Known Activations