© 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. 119392
    Prev
    Next
    INDEX
    Explanations

    Floyd Mayweather Jr.Elastic propertiesZimbabwe swears

    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
    ร้อน
    -0.06
    三角
    -0.06
     bravely
    -0.06
    ettore
    -0.06
     умер
    -0.06
     三角
    -0.06
    㑒
    -0.06
     convolutional
    -0.06
    VOLUME
    -0.06
     mohou
    -0.05
    POSITIVE LOGITS
     আত্মসমর্পণ
    0.06
    ้
    0.06
     negotiations
    0.06
     return
    0.06
     lawsuit
    0.06
     parfum
    0.06
    nextSend
    0.06
     प्रोफेशनल
    0.06
     minimalism
    0.06
    Week
    0.06
    Activations Density 0.011%

    No Known Activations