© 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. 1673
    Prev
    Next
    INDEX
    Explanations

    multilingual text detection

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

    learning outcomes, Stephanie, assuming, years, create function

    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
    ,
    0.50
    ch
    0.49
    が
    0.48
    でも
    0.47
     harmless
    0.46
     outflow
    0.46
    で
    0.46
    量
    0.45
    にお
    0.45
     award
    0.45
    POSITIVE LOGITS
    rafpunkte
    0.53
     männ
    0.49
    issaient
    0.48
    હેરા
    0.47
     ίδια
    0.47
     damal
    0.47
     सवारी
    0.47
     पुरुष
    0.46
     পরিপ্রে
    0.46
     Antennes
    0.46
    Activations Density 0.000%

    No Known Activations