© 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. 116934
    Prev
    Next
    INDEX
    Explanations

    time, Services, 4, second, sport

    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
    ੧
    -0.06
    是用
    -0.06
    हन
    -0.06
     acknowled
    -0.06
     thorough
    -0.06
     results
    -0.06
     Saudi
    -0.06
     middel
    -0.06
     dishonesty
    -0.06
    ड़े
    -0.06
    POSITIVE LOGITS
     desde
    0.06
    Neue
    0.06
    另一
    0.06
     cada
    0.06
     mangas
    0.06
    from
    0.06
     regla
    0.06
     বিপজ্জনক
    0.06
     zwy
    0.06
    stops
    0.05
    Activations Density 0.005%

    No Known Activations