© 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. 116791
    Prev
    Next
    INDEX
    Explanations

    list item structure

    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
     if
    -0.09
     nếu
    -0.07
    If
    -0.07
     jika
    -0.07
     если
    -0.07
     eğer
    -0.06
    ถ้า
    -0.06
     także
    -0.06
     النسب
    -0.06
     ویژگی
    -0.06
    POSITIVE LOGITS
     chúng
    0.07
     one
    0.07
     pochi
    0.07
    大手
    0.07
     одним
    0.07
    ↵
    0.07
     an
    0.06
     सारे
    0.06
    と思われる
    0.06
     einer
    0.06
    Activations Density 0.002%

    No Known Activations