© 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. 161188
    Prev
    Next
    INDEX
    Explanations

    multilingual text detection

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

    required by

    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
    人物
    0.50
    行列
    0.49
    流域
    0.47
    idc
    0.46
    您
    0.46
    صة
    0.46
    困难
    0.45
    支援
    0.45
    宮
    0.45
    事件
    0.44
    POSITIVE LOGITS
     పై
    0.55
     проде
    0.50
     выбро
    0.50
     исправ
    0.49
     చేశ
    0.49
     этом
    0.48
     смы
    0.48
     пло
    0.47
     доста
    0.46
    istung
    0.46
    Activations Density 0.001%

    No Known Activations