© 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. 116806
    Prev
    Next
    INDEX
    Explanations

    sql query parts

    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
    While
    -0.07
     cca
    -0.07
     walaupun
    -0.06
     rgba
    -0.06
     også
    -0.06
     även
    -0.06
     също
    -0.06
     excursion
    -0.06
    뭔
    -0.06
     terwijl
    -0.06
    POSITIVE LOGITS
    我们要
    0.06
    economic
    0.06
    পরী
    0.06
    但这
    0.06
     основных
    0.06
     ideological
    0.06
    介绍
    0.05
    ȇ
    0.05
    立即
    0.05
    ান্দ
    0.05
    Activations Density 0.003%

    No Known Activations