© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203931
    Prev
    Next
    INDEX
    Explanations

    Japanese sentence endings (な)

    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_6_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
    ם
    0.92
    ي
    0.89
    ah
    0.88
     duh
    0.88
    )
    0.85
    IZED
    0.84
    CID
    0.82
     solicitar
    0.81
     gastroenter
    0.81
     scrap
    0.81
    POSITIVE LOGITS
     (
    1.12
    在
    0.94
    니
    0.91
    У
    0.90
    И
    0.89
    つ
    0.86
    ни
    0.86
    bulan
    0.86
    А
    0.86
    м
    0.83
    Activations Density 0.001%

    No Known Activations