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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110167
    Prev
    Next
    INDEX
    Explanations

    japanese verb endings imas/ita

    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
    é
    1.34
    _
    1.27
    ר
    1.18
    ر
    1.15
    -
    1.12
    OS
    1.05
    ão
    1.04
    е
    1.04
    ų
    1.04
     valves
    0.99
    POSITIVE LOGITS
    in
    1.32
    ו
    1.16
    ا
    1.13
    to
    1.02
    মাত্র
    1.00
    on
    0.96
    de
    0.94
    re
    0.93
    am
    0.88
    c
    0.87
    Activations Density 0.001%

    No Known Activations