© 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. 71062
    Prev
    Next
    INDEX
    Explanations

    number of people

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

    number of

    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
     هز
    0.45
     مگر
    0.45
     肌
    0.45
     ฝ
    0.42
     ヒ
    0.41
     హ
    0.40
     ゴールド
    0.40
     során
    0.40
     pusher
    0.40
    politik
    0.39
    POSITIVE LOGITS
    人數
    0.55
     (%)
    0.54
    人数
    0.51
    有多少
    0.51
     каждым
    0.49
     meningkat
    0.49
     Anzahl
    0.48
    percentage
    0.46
     antal
    0.46
     sayısı
    0.45
    Activations Density 0.074%

    No Known Activations