© 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. 117343
    Prev
    Next
    INDEX
    Explanations

    various foreign languages

    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
     each
    -0.07
     orientado
    -0.06
     každý
    -0.06
     высокие
    -0.06
    న్నీ
    -0.06
     fiecare
    -0.06
     conoz
    -0.06
     herbicides
    -0.06
     каждом
    -0.06
     каждый
    -0.06
    POSITIVE LOGITS
     various
    0.07
     различных
    0.07
    various
    0.07
     çeşitli
    0.06
     különböző
    0.06
     różnych
    0.06
     různých
    0.06
     كيفية
    0.06
     不同
    0.06
    不同
    0.06
    Activations Density 0.010%

    No Known Activations