© 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. 116340
    Prev
    Next
    INDEX
    Explanations

    World War II

    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
     ضع
    -0.07
     Keine
    -0.07
     Tuttavia
    -0.07
    strstr
    -0.07
     pariy
    -0.06
     ไม่มี
    -0.06
     doanh
    -0.06
     करो
    -0.06
     phải
    -0.06
    芑
    -0.06
    POSITIVE LOGITS
     purpose
    0.07
    purpose
    0.06
    ursery
    0.06
     ills
    0.06
     პირ
    0.05
     materialize
    0.05
     ayudarte
    0.05
     purposes
    0.05
     unmatched
    0.05
    目的是
    0.05
    Activations Density 0.005%

    No Known Activations