© 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. 124567
    Prev
    Next
    INDEX
    Explanations

    business/industry contexts

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

    using or applying something

    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
    s
    0.59
    ל
    0.53
     explain
    0.51
    ς
    0.50
     explained
    0.49
    ;
    0.49
     explicar
    0.48
     /*
    0.47
    ה
    0.47
    a
    0.46
    POSITIVE LOGITS
     причиной
    0.56
     이용하여
    0.54
     يستخدم
    0.53
     사용하여
    0.52
     använder
    0.51
     используя
    0.50
     肉
    0.47
     ഞ
    0.47
     нашим
    0.47
     বাহিনী
    0.46
    Activations Density 0.000%

    No Known Activations