© 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. 119744
    Prev
    Next
    INDEX
    Explanations

    numbers followed by closing parenthesis

    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
     or
    -0.06
     величе
    -0.06
     pursuant
    -0.06
     nor
    -0.06
    FOUND
    -0.06
     প্রতিনিধ
    -0.06
     enfant
    -0.06
    found
    -0.06
    因子
    -0.05
     මහ
    -0.05
    POSITIVE LOGITS
     gọi
    0.06
    𝚐
    0.06
     კონ
    0.06
     ophthalm
    0.06
     నా
    0.06
    рованием
    0.06
    𝚌
    0.06
     тази
    0.06
     hỗ
    0.06
     каждый
    0.05
    Activations Density 0.005%

    No Known Activations