© 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. 34-GEMMASCOPE-RES-131K
    7. 117422
    Prev
    Next
    INDEX
    Explanations

    quiz and test questions

    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_34/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
    гӀ
    -0.88
     obrazu
    -0.76
    licting
    -0.73
    畫面
    -0.72
     pokoj
    -0.71
    遲
    -0.68
     Hamlin
    -0.67
     Garnett
    -0.67
    kole
    -0.66
    sistance
    -0.65
    POSITIVE LOGITS
     quiz
    6.09
     Quiz
    4.91
    quiz
    4.84
     quizzes
    4.75
    Quiz
    4.56
    QUIZ
    3.63
     QUIZ
    3.63
     Quizzes
    3.30
     test
    2.50
     trivia
    2.36
    Activations Density 0.086%

    No Known Activations