© 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. 1773
    Prev
    Next
    INDEX
    Explanations

    common word followed by a specific noun

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

    Vietnamese language and culture

    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
     вследствие
    0.47
    isy
    0.46
     تعریف
    0.46
     EDL
    0.46
     ++)
    0.45
     दाखिल
    0.45
    )==
    0.44
    ўкі
    0.44
    +")
    0.44
    ണ്ഡ
    0.44
    POSITIVE LOGITS
    ט
    0.56
    מ
    0.56
    getCurrent
    0.51
    Зна
    0.50
    Че
    0.49
    ש
    0.49
    الأ
    0.49
    מר
    0.48
    အ
    0.48
    জ
    0.47
    Activations Density 0.000%

    No Known Activations