© 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. 116936
    Prev
    Next
    INDEX
    Explanations

    countries and place names

    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
     minha
    -0.07
     мой
    -0.06
     meinem
    -0.06
    繁忙時間
    -0.06
     میرے
    -0.06
     arbeiten
    -0.06
    我
    -0.06
     my
    -0.06
    も
    -0.06
     combinado
    -0.06
    POSITIVE LOGITS
     when
    0.06
    ્લા
    0.06
     केंद्रीय
    0.06
     ఇప్పుడు
    0.06
     திட
    0.06
     deri
    0.06
     the
    0.06
    現在
    0.06
    primarily
    0.06
     новым
    0.06
    Activations Density 0.004%

    No Known Activations