© 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. 117333
    Prev
    Next
    INDEX
    Explanations

    multi-lingual punctuation

    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
     ابتدا
    -0.06
     origem
    -0.06
    ")
    -0.06
     अधिव
    -0.06
     unbek
    -0.05
     बदली
    -0.05
    ");
    -0.05
    )。
    -0.05
    Explore
    -0.05
    );
    -0.05
    POSITIVE LOGITS
    我們
    0.07
    ’!
    0.07
    !...
    0.06
     zugleich
    0.06
     !
    0.06
    വേശ
    0.06
    !";
    0.06
     kapital
    0.06
    નેસ
    0.06
     tận
    0.06
    Activations Density 0.025%

    No Known Activations