© 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. 31317
    Prev
    Next
    INDEX
    Explanations

    calling the city

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

    * lists

    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
    拉
    0.52
    年底
    0.45
     முதலிய
    0.44
    大
    0.43
    银
    0.43
    姑
    0.43
    自定义
    0.43
    加
    0.42
    说明
    0.42
    灵
    0.42
    POSITIVE LOGITS
    clientes
    0.49
    price
    0.47
    вів
    0.46
    cture
    0.45
    fc
    0.45
    tev
    0.45
    ্লেখ
    0.44
    tk
    0.44
    腫
    0.44
     tsy
    0.44
    Activations Density 0.000%

    No Known Activations