© 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. 104410
    Prev
    Next
    INDEX
    Explanations

    you can, an ice, when arrives, Vickers called

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

    passengers, circuits, or repositories

    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
    页面存档备份
    0.51
    狀
    0.46
    排行榜
    0.44
    صول
    0.43
    截图
    0.43
    排行
    0.43
    लीम
    0.42
     ڈال
    0.42
    羲
    0.42
    疑问
    0.42
    POSITIVE LOGITS
     excite
    0.44
     electronically
    0.43
     immediately
    0.43
     RR
    0.42
     where
    0.42
    3
    0.42
     inform
    0.42
     nitrogen
    0.42
     patent
    0.41
    ிகள்
    0.41
    Activations Density 0.000%

    No Known Activations