© 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. 241053
    Prev
    Next
    INDEX
    Explanations

    names in various languages

    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
    ұ
    0.49
     мор
    0.48
     போக்குவரத்து
    0.48
     यात्री
    0.47
     कनेक्टिविटी
    0.47
     בז
    0.47
    ugg
    0.46
     paes
    0.46
     Morg
    0.45
    橑
    0.45
    POSITIVE LOGITS
    िकारक
    0.47
     منصوبہ
    0.46
    ライス
    0.46
    殿
    0.45
    命令
    0.45
    文件名
    0.44
    影片
    0.43
    いです
    0.43
     hijos
    0.43
    英文
    0.42
    Activations Density 0.001%

    No Known Activations