© 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. 128429
    Prev
    Next
    INDEX
    Explanations

    digital converter, bit number

    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
     সংখ্যালঘু
    -0.07
     шан
    -0.07
     diag
    -0.06
     বিপ্লবী
    -0.06
     apost
    -0.06
    দ্র
    -0.06
    gesetz
    -0.06
     sour
    -0.06
     attitudes
    -0.06
     defiant
    -0.06
    POSITIVE LOGITS
     ร้าน
    0.07
    屋内
    0.06
     weddings
    0.06
    romechanical
    0.06
     sama
    0.06
     indoors
    0.06
     限
    0.06
    দিনই
    0.06
     本体
    0.06
     Dwyer
    0.06
    Activations Density 0.001%

    No Known Activations