© 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. 52383
    Prev
    Next
    INDEX
    Explanations

    non-english content or diverse languages

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

    building blocks

    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
    他們
    0.59
    他们
    0.49
     सरपंच
    0.48
    他们在
    0.47
    قر
    0.46
    瓶
    0.46
    博士
    0.46
    主任
    0.45
    prima
    0.45
    文字
    0.45
    POSITIVE LOGITS
     갑
    0.51
     일반
    0.47
     giám
    0.47
     iler
    0.47
     uku
    0.46
     Fried
    0.46
     풍
    0.46
     정리
    0.46
    یکس
    0.46
     ดวง
    0.46
    Activations Density 0.000%

    No Known Activations