© 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. 234635
    Prev
    Next
    INDEX
    Explanations

    multilingual words and phrases

    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
    มัน
    0.52
     RANDOM
    0.51
    thin
    0.46
    哥
    0.43
    随机
    0.43
    行き
    0.42
     tannin
    0.42
    ประโยชน์
    0.42
    阵
    0.42
     hiểu
    0.41
    POSITIVE LOGITS
     décès
    0.54
     άλλ
    0.50
     possível
    0.49
     restante
    0.46
     încă
    0.46
     geändert
    0.45
     Manip
    0.45
    ammable
    0.45
    সিডেন্ট
    0.44
    spersed
    0.44
    Activations Density 0.001%

    No Known Activations