© 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. 117460
    Prev
    Next
    INDEX
    Explanations

    numbers and code syntax

    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
     andDevice
    -0.07
     ሶ
    -0.06
    同时
    -0.06
    绎
    -0.06
    ゆっくり
    -0.06
     homen
    -0.06
     আনুষ্ঠানিকভাবে
    -0.06
     Bored
    -0.06
    Forget
    -0.06
    三重
    -0.06
    POSITIVE LOGITS
     como
    0.06
     یا
    0.06
     our
    0.06
    new
    0.06
     like
    0.06
     new
    0.06
    como
    0.06
     geist
    0.06
    roquois
    0.06
    как
    0.06
    Activations Density 0.001%

    No Known Activations