© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130854
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

    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
     nueva
    -0.08
     made
    -0.08
     nuevos
    -0.07
     nuovi
    -0.07
     новой
    -0.07
     новая
    -0.07
     الجديدة
    -0.07
     nouveaux
    -0.06
     nuevas
    -0.06
     new
    -0.06
    POSITIVE LOGITS
    :
    0.07
     zadovol
    0.07
    Zhao
    0.07
     sixteen
    0.06
     শ্রেণ
    0.06
    后者
    0.06
     zufrieden
    0.06
    愍
    0.06
     latter
    0.06
     Zhao
    0.06
    Activations Density 0.004%

    No Known Activations