© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200219
    Prev
    Next
    INDEX
    Explanations

    non-English words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    apeutics
    0.41
    чке
    0.40
    дикатор
    0.40
    eritud
    0.39
    க்ச
    0.39
    舝
    0.39
    poque
    0.39
    欱
    0.39
    ᠮ
    0.39
     করির
    0.39
    POSITIVE LOGITS
     karena
    0.50
     व्याख्या
    0.44
     મળ
    0.43
     由于
    0.43
     እንዲሁ
    0.43
     因为
    0.43
    发现
    0.43
     Swansea
    0.42
    游
    0.42
     fluvial
    0.42
    Activations Density 0.003%

    No Known Activations