© 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. 118451
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

    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
     совершенно
    -0.06
    ോളം
    -0.06
    আরও
    -0.06
     VERY
    -0.06
     soit
    -0.06
    .
    -0.06
     divent
    -0.06
     very
    -0.06
    成為
    -0.06
     아래
    -0.06
    POSITIVE LOGITS
    愿
    0.06
     времена
    0.06
     첫
    0.06
     ваша
    0.06
     alkohol
    0.06
     Nazi
    0.06
    मोन
    0.06
    初の
    0.05
    时代的
    0.05
    ડિયો
    0.05
    Activations Density 0.001%

    No Known Activations