© 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. 145643
    Prev
    Next
    INDEX
    Explanations

    foreign language words and punctuation

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

    questions asking "what"

    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
    ियन
    0.50
    ersburg
    0.47
    quan
    0.46
    kappa
    0.45
    oader
    0.45
    簱
    0.44
     पटा
    0.44
    使用了
    0.43
    sPath
    0.43
     Bagley
    0.43
    POSITIVE LOGITS
    っていう
    0.55
    !..
    0.48
     স্বাক্ষর
    0.48
     undang
    0.48
     authorize
    0.47
     შეგი
    0.46
     ouvre
    0.46
    +","+
    0.45
    之間
    0.45
     edilmesi
    0.45
    Activations Density 0.000%

    No Known Activations