© 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. 119246
    Prev
    Next
    INDEX
    Explanations

    each or distribution

    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
    -(
    -0.06
     nhé
    -0.06
     أيضا
    -0.06
    的具体
    -0.06
    例如
    -0.06
     cevap
    -0.06
    有时
    -0.06
    总是
    -0.06
    BOUND
    -0.05
    POSITIVE LOGITS
    每个
    0.07
     when
    0.07
     you
    0.07
     Inicial
    0.07
     genus
    0.06
     每个
    0.06
     เริ่ม
    0.06
     ஒவ்வொரு
    0.06
     มัน
    0.06
    每個
    0.06
    Activations Density 0.003%

    No Known Activations