© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130791
    Prev
    Next
    INDEX
    Explanations

    protocols and methods description

    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
     مناسب
    -0.08
     for
    -0.07
     vhodné
    -0.06
     offerings
    -0.06
     подой
    -0.06
    适合
    -0.06
     ઘણા
    -0.06
     빛
    -0.06
     জেনে
    -0.05
    適合
    -0.05
    POSITIVE LOGITS
     поскольку
    0.07
    aliyet
    0.07
     Поскольку
    0.06
    這樣子
    0.06
    ໂດຍ
    0.06
     according
    0.06
     최종
    0.06
     sebagaimana
    0.06
    ревнования
    0.06
     correspondence
    0.06
    Activations Density 0.002%

    No Known Activations