© 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. 10059
    Prev
    Next
    INDEX
    Explanations

    This pictures

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

    visual representation or drawing

    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
     déficit
    0.35
    閲
    0.34
     deficit
    0.34
     ข้อ
    0.33
     buddhav
    0.33
    语法
    0.32
     dét
    0.32
     complementary
    0.32
     idioms
    0.32
    δοση
    0.32
    POSITIVE LOGITS
    如下图
    1.32
    下图
    1.20
     pictured
    1.02
    <start_of_image>
    1.02
    ![](
    0.98
    如图
    0.96
    pictured
    0.93
    ↵↵↵↵↵↵↵↵↵
    0.93
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.92
    ↵↵↵↵↵↵↵
    0.88
    Activations Density 0.146%

    No Known Activations