© 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. 128469
    Prev
    Next
    INDEX
    Explanations

    UI elements and names

    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
     somehow
    -0.07
     Somehow
    -0.06
     for
    -0.06
     at
    -0.06
     оказывается
    -0.06
     ஒன்ற
    -0.06
     গিয়া
    -0.06
     hasattr
    -0.06
    dang
    -0.06
     pedig
    -0.06
    POSITIVE LOGITS
    と呼ばれる
    0.06
     calculate
    0.06
     મુખ્ય
    0.06
     deviations
    0.06
     advertised
    0.06
     মূল
    0.06
    čni
    0.06
    受欢迎
    0.06
     কোভিড
    0.06
     primary
    0.06
    Activations Density 0.001%

    No Known Activations