© 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. 130578
    Prev
    Next
    INDEX
    Explanations

    navigation separators

    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
    >≥</
    -0.06
    他在
    -0.06
     ওষুধ
    -0.06
     dalam
    -0.06
     в
    -0.06
     tedy
    -0.06
     poderoso
    -0.06
    着
    -0.06
    MSG
    -0.06
     Pavel
    -0.06
    POSITIVE LOGITS
    ,
    0.07
    いくつかの
    0.06
     استفاده
    0.06
     سنو
    0.06
     使用
    0.06
     Jeans
    0.06
     beberapa
    0.06
     استخدام
    0.05
     value
    0.05
     varias
    0.05
    Activations Density 0.004%

    No Known Activations