© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13555
    Prev
    Next
    INDEX
    Explanations

    Japanese names and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    henswürdigkeiten
    -1.87
    呖
    -1.66
    payers
    -1.65
    llten
    -1.63
     캐릭터
    -1.59
     unrelenting
    -1.56
    万物
    -1.55
    Люди
    -1.54
    ;
    -1.51
     ตา
    -1.50
    POSITIVE LOGITS
     Which
    1.91
     “
    1.84
     principalmente
    1.73
    ⩕
    1.73
     feront
    1.69
     frequentemente
    1.68
    if
    1.66
    痉
    1.66
    which
    1.65
     большая
    1.63
    Activations Density 0.041%

    No Known Activations