© 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. 60704
    Prev
    Next
    INDEX
    Explanations

    is called the internet

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

    attention mechanisms and similarity

    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
     малы
    0.51
     diseño
    0.50
    τί
    0.49
    НА
    0.49
     процесса
    0.46
     Tilly
    0.45
    薰
    0.45
     훨씬
    0.44
    itipi
    0.44
    にく
    0.44
    POSITIVE LOGITS
     تكلم
    0.45
    吧
    0.44
     vede
    0.43
     sprechen
    0.42
     يو
    0.41
    塭
    0.41
     ==>
    0.40
    看到了
    0.39
    テーション
    0.39
    ശേഷം
    0.39
    Activations Density 0.000%

    No Known Activations