© 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. 129651
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
     الحرب
    -0.06
     eighteenth
    -0.06
     special
    -0.06
     বিশ্বাসের
    -0.06
     sixties
    -0.05
     eighties
    -0.05
     seventeenth
    -0.05
     twelfth
    -0.05
     तीसरा
    -0.05
    лес
    -0.05
    POSITIVE LOGITS
     nemmeno
    0.07
     durchaus
    0.06
    其
    0.06
    都沒有
    0.06
     missão
    0.06
    iliki
    0.06
     compone
    0.06
     неуда
    0.06
     otros
    0.06
    都不会
    0.06
    Activations Density 0.005%

    No Known Activations