© 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. 175166
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    treated equally

    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
    and
    0.56
    ↵↵↵
    0.51
    ↵
    0.46
    main
    0.46
     as
    0.45
    Main
    0.45
    User
    0.45
    as
    0.44
     and
    0.43
    loop
    0.43
    POSITIVE LOGITS
     Sağ
    0.51
     ઝડ
    0.49
    졀
    0.48
     ধর্ষণ
    0.48
     ভুট্ট
    0.46
     черный
    0.46
    碎
    0.46
     ઝ
    0.45
     ಶೆ
    0.45
     STARTED
    0.45
    Activations Density 0.000%

    No Known Activations