© 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. 128847
    Prev
    Next
    INDEX
    Explanations

    countries and states

    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
    hasOwnProperty
    -0.06
    ？
    -0.06
     Temos
    -0.06
     practicality
    -0.06
    ້ອຍ
    -0.06
    容易
    -0.06
     illustration
    -0.06
     Specifically
    -0.06
     خصوص
    -0.06
     especially
    -0.06
    POSITIVE LOGITS
     четыре
    0.07
     giữ
    0.07
    ittings
    0.06
    начально
    0.06
     mirror
    0.06
     ¼
    0.06
    Forever
    0.06
     uit
    0.06
    deen
    0.06
    prache
    0.06
    Activations Density 0.019%

    No Known Activations