© 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. 117742
    Prev
    Next
    INDEX
    Explanations

    date formats: Jan, PM, MM, USD, days, monthNames

    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
     then
    -0.07
     dvě
    -0.06
     दिवशी
    -0.06
    semi
    -0.06
     dwie
    -0.06
    hen
    -0.06
     من
    -0.05
    ìn
    -0.05
    ake
    -0.05
    energie
    -0.05
    POSITIVE LOGITS
     això
    0.06
    骜
    0.06
     تكعيب
    0.06
     رغم
    0.06
    regardless
    0.06
     egyéb
    0.06
     Ashram
    0.06
     Apesar
    0.06
    葡萄酒
    0.06
     데이터
    0.06
    Activations Density 0.001%

    No Known Activations