© 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. 119898
    Prev
    Next
    INDEX
    Explanations

    issues, problems, or trouble

    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
     verbeter
    -0.07
     lessons
    -0.06
     تبدیلی
    -0.06
    Certain
    -0.06
     Certain
    -0.06
    Despite
    -0.06
     Jehová
    -0.06
    准确
    -0.06
     vlastní
    -0.06
     tools
    -0.06
    POSITIVE LOGITS
     вопросы
    0.07
     relacionada
    0.06
     relacionadas
    0.06
    fisherman
    0.06
    gaver
    0.06
     questões
    0.06
     astrophysical
    0.06
     তোলা
    0.06
    बाबत
    0.06
     вопросам
    0.06
    Activations Density 0.017%

    No Known Activations