© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149899
    Prev
    Next
    INDEX
    Explanations

    之作

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    而
    1.50
     而
    1.35
    而出
    1.13
    而在
    1.08
     while
    1.07
    而被
    1.06
     Mentre
    1.00
     mentre
    1.00
     mientras
    0.97
     অথচ
    0.95
    POSITIVE LOGITS
    類的
    1.35
    нных
    0.86
    нные
    0.86
    Tree
    0.83
    |,
    0.79
    нную
    0.76
    Wei
    0.75
    Democrats
    0.75
    humid
    0.74
    Editor
    0.73
    Activations Density 0.000%

    No Known Activations