© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70957
    Prev
    Next
    INDEX
    Explanations

    Chinese negative particles; English determiners

    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
     Каждый
    -2.92
    小孩子
    -2.81
     of
    -2.78
     kekasih
    -2.73
     mengajar
    -2.70
    る
    -2.67
     usai
    -2.64
     pelaksanaan
    -2.64
     pernikahan
    -2.58
     achten
    -2.58
    POSITIVE LOGITS
     всѣ
    2.86
    ları
    2.47
     parachoque
    2.45
    啻
    2.36
    馀
    2.33
    fatalError
    2.33
    思议
    2.30
    ኵ
    2.30
    逦
    2.30
     endforeach
    2.28
    Activations Density 0.000%

    No Known Activations