© 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. 109767
    Prev
    Next
    INDEX
    Explanations

    coordinating, party, reduce, Swords, train

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

    keywords used in programming

    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
    居民
    0.51
    被
    0.48
    向
    0.46
    習
    0.44
    補
    0.44
    将
    0.44
    副
    0.44
    籍
    0.43
    有一個
    0.43
    最大
    0.43
    POSITIVE LOGITS
     ночь
    0.53
     Noct
    0.52
     იმ
    0.52
     Liss
    0.52
    leri
    0.49
    ină
    0.49
    öne
    0.48
    luoro
    0.48
     fero
    0.47
     Arbor
    0.47
    Activations Density 0.001%

    No Known Activations