© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 244609
    Prev
    Next
    INDEX
    Explanations

    resulting visual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     автобу
    0.60
     корпу
    0.53
    barrow
    0.51
     শাহরুখ
    0.49
     за
    0.48
     است
    0.48
    艙
    0.47
     ತ
    0.46
     சுற்றுலா
    0.46
     корпуса
    0.46
    POSITIVE LOGITS
    라
    0.50
    ামিন
    0.49
    اف
    0.46
    명
    0.46
     interviewer
    0.46
    CLAS
    0.45
    লোক
    0.45
    블
    0.44
    ZQ
    0.44
     lengthening
    0.44
    Activations Density 0.000%

    No Known Activations