© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92254
    Prev
    Next
    INDEX
    Explanations

    Korean leader

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

    describing choices or conditions

    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
    Negative Logits
    є
    0.47
     camps
    0.47
     intractable
    0.47
     ተ
    0.46
     CURLOPT
    0.44
    ঞ্জাম
    0.44
     rockers
    0.44
     succulents
    0.44
     solution
    0.43
     imprecise
    0.43
    POSITIVE LOGITS
    مدينة
    0.54
    рых
    0.45
     würde
    0.44
    стройства
    0.44
    皇帝
    0.43
    羨
    0.43
    would
    0.42
    投标文件
    0.41
    classify
    0.41
    慣
    0.41
    Activations Density 0.002%

    No Known Activations