© 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. 119678
    Prev
    Next
    INDEX
    Explanations

    foreign language snippets

    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
     those
    -0.06
     对于
    -0.06
     thoſe
    -0.06
     Although
    -0.06
     Those
    -0.06
     இவற்ற
    -0.06
     Kyoto
    -0.06
     Despite
    -0.06
     ഞാൻ
    -0.06
    京都
    -0.05
    POSITIVE LOGITS
     auf
    0.07
     på
    0.06
     wang
    0.06
     почти
    0.06
     lebih
    0.06
     cca
    0.06
    两人
    0.06
     języ
    0.06
     puede
    0.06
     более
    0.06
    Activations Density 0.003%

    No Known Activations