© 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. 129934
    Prev
    Next
    INDEX
    Explanations

    specifications related to numbers and IO

    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
    What
    -0.07
    Three
    -0.06
     untuk
    -0.06
     Two
    -0.06
     |
    -0.06
    Some
    -0.06
     keep
    -0.06
    Two
    -0.06
     Some
    -0.06
     loader
    -0.06
    POSITIVE LOGITS
     ഞങ്ങൾ
    0.07
    我们会
    0.07
    我們會
    0.07
     слегка
    0.07
    ¹,
    0.07
     jų
    0.07
     такой
    0.07
     вас
    0.07
    我们要
    0.06
     chúng
    0.06
    Activations Density 0.133%

    No Known Activations