© 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. 86995
    Prev
    Next
    INDEX
    Explanations

    creates movie times

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

    tools and techniques

    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
    人类
    0.51
    isional
    0.46
    λά
    0.43
    larını
    0.42
    inic
    0.42
    ScreenBinding
    0.41
    <0x80>
    0.41
    iş
    0.41
    Wendy
    0.40
    اسلام
    0.40
    POSITIVE LOGITS
     less
    0.52
     Costume
    0.52
     Ch
    0.51
     ハンド
    0.51
     Culture
    0.50
     luscious
    0.49
     culture
    0.49
     freshmen
    0.48
     Dancing
    0.48
     diaper
    0.48
    Activations Density 0.000%

    No Known Activations