© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130121
    Prev
    Next
    INDEX
    Explanations

    UNHCR, World Bank, Children

    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
     también
    -0.07
     ყველა
    -0.07
     também
    -0.06
     cũng
    -0.06
     vencedor
    -0.06
     industriel
    -0.06
     Raised
    -0.06
     familia
    -0.06
     phiên
    -0.06
    லோக
    -0.06
    POSITIVE LOGITS
     partnership
    0.07
     کیس
    0.06
     posting
    0.06
    ަށް
    0.06
     actively
    0.06
     प्रोग्राम
    0.06
     aport
    0.06
    Agreement
    0.06
     Latex
    0.06
     bipartisan
    0.05
    Activations Density 0.003%

    No Known Activations