© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57481
    Prev
    Next
    INDEX
    Explanations

    japanese sentence endings: yo, ne, ka

    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_11_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
    ished
    0.56
    ଷ୍
    0.56
     Const
    0.53
    ଥ
    0.53
    ер
    0.52
     muscular
    0.52
     మద్యం
    0.52
     threatening
    0.50
     ಅಪಾಯ
    0.50
    小さい
    0.49
    POSITIVE LOGITS
    "
    0.67
    Work
    0.61
    Faction
    0.59
    Impact
    0.59
    Hai
    0.57
    Waar
    0.56
    Aluno
    0.55
    Verified
    0.55
     היה
    0.54
    Eksterne
    0.54
    Activations Density 0.000%

    No Known Activations