© 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. 179103
    Prev
    Next
    INDEX
    Explanations

    transportation and logistics

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

    listing explanations or options

    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
    数组
    0.48
    楼
    0.47
    一个
    0.46
    ۰
    0.46
    墙
    0.46
    列表
    0.46
    各种
    0.45
    书
    0.45
    块
    0.45
    声明
    0.45
    POSITIVE LOGITS
     рр
    0.54
     транспорти
    0.50
     транспорта
    0.45
    тка
    0.45
     transporte
    0.44
     Avion
    0.44
     ICA
    0.44
    ја
    0.44
    legt
    0.44
     ಕಂಚ
    0.43
    Activations Density 0.000%

    No Known Activations