© 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. 209023
    Prev
    Next
    INDEX
    Explanations

    strategies in, information here, originated in

    np_acts-logits-general · gemini-2.5-flash-lite

    language variations, spelling, printing

    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
    克兰
    0.47
    澧
    0.47
     diketahui
    0.47
    tım
    0.47
    ناصر
    0.47
    คาร
    0.47
    OneDrive
    0.47
     звезды
    0.46
    耀
    0.46
     esteja
    0.46
    POSITIVE LOGITS
     キッチン
    0.50
     کت
    0.47
     tires
    0.47
    变成了
    0.46
    rang
    0.46
    ipi
    0.45
     DAT
    0.45
    ành
    0.44
    progressBar
    0.44
     ال
    0.44
    Activations Density 0.001%

    No Known Activations