© 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. 117079
    Prev
    Next
    INDEX
    Explanations

    mathematical equations with numbers

    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
     আবারও
    -0.07
     clandestine
    -0.06
    られています
    -0.06
     incluyendo
    -0.06
     recklessly
    -0.06
     waived
    -0.06
     yli
    -0.06
     بالإضافة
    -0.06
     최근
    -0.06
     снова
    -0.06
    POSITIVE LOGITS
     LANGUAGES
    0.06
     ARTICLES
    0.06
    さが
    0.06
     claimants
    0.06
    ண்ப
    0.06
    none
    0.06
    開始
    0.06
    .
    0.06
     világ
    0.06
     шка
    0.06
    Activations Density 0.003%

    No Known Activations