© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128798
    Prev
    Next
    INDEX
    Explanations

    HTML tag closing bracket

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     danas
    -0.07
     delayed
    -0.06
    delayed
    -0.06
     för
    -0.06
     today
    -0.06
     dabei
    -0.06
    AddNew
    -0.06
     Delayed
    -0.06
    当时
    -0.06
     adding
    -0.06
    POSITIVE LOGITS
     rekan
    0.07
    껏
    0.07
     相
    0.06
     
    0.06
    都被
    0.06
     على
    0.06
    アプリケーション
    0.06
     様
    0.06
    xmax
    0.06
    相
    0.06
    Activations Density 0.001%

    No Known Activations