© 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. 116890
    Prev
    Next
    INDEX
    Explanations

    change or update

    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
     mencipt
    -0.06
     Mô
    -0.06
     quản
    -0.06
     sân
    -0.06
     개념
    -0.06
    がありますが
    -0.06
    рее
    -0.06
    ่อน
    -0.06
     দ্বিত
    -0.06
    POSITIVE LOGITS
     changing
    0.07
     очередной
    0.07
     changed
    0.06
     পানির
    0.06
    如今
    0.06
    每一
    0.06
     never
    0.06
    真實
    0.06
     outra
    0.06
     every
    0.06
    Activations Density 0.002%

    No Known Activations