© 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. 118638
    Prev
    Next
    INDEX
    Explanations

    open source licenses

    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
    ילה
    -0.06
     achievable
    -0.06
     ছিলোনা
    -0.06
     нём
    -0.06
     være
    -0.06
     ...");
    -0.06
     için
    -0.06
     இத
    -0.06
    Ken
    -0.05
     notable
    -0.05
    POSITIVE LOGITS
     oftentimes
    0.07
     हमारे
    0.07
     наші
    0.07
    Từ
    0.07
     nuestro
    0.06
     unsere
    0.06
    根據
    0.06
     nuestros
    0.06
     यावेळी
    0.06
     डिजाइनर
    0.06
    Activations Density 0.002%

    No Known Activations