© 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. 118092
    Prev
    Next
    INDEX
    Explanations

    data storage and indexing

    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
    بلغ
    -0.06
     طلب
    -0.06
     thematic
    -0.06
    邀请
    -0.06
    thema
    -0.06
    REQUEST
    -0.06
     Request
    -0.06
    using
    -0.05
    ご連絡
    -0.05
     श्रेय
    -0.05
    POSITIVE LOGITS
    日志
    0.07
     знаю
    0.06
    有關
    0.06
     logs
    0.06
    有关
    0.06
    这是
    0.06
    低于
    0.06
     rested
    0.06
     rules
    0.06
     σχετικά
    0.06
    Activations Density 0.006%

    No Known Activations