© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118387
    Prev
    Next
    INDEX
    Explanations

    image file extensions and domain 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
    stopPropagation
    -0.07
    nienia
    -0.06
    проек
    -0.06
    мами
    -0.06
    WARN
    -0.06
    不同的
    -0.06
     The
    -0.06
    OrDefault
    -0.06
    roffen
    -0.06
    做一个
    -0.06
    POSITIVE LOGITS
    での
    0.07
     marbles
    0.06
     виды
    0.06
     secondaires
    0.06
    িক্যাল
    0.06
     achieves
    0.06
     الكثير
    0.06
     lends
    0.06
    에서의
    0.06
    Expert
    0.06
    Activations Density 0.001%

    No Known Activations