© 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. 120485
    Prev
    Next
    INDEX
    Explanations

    links and questions

    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
    Already
    -0.07
     already
    -0.07
    已经
    -0.06
     Posteriormente
    -0.06
     już
    -0.06
     கண்டு
    -0.06
     כבר
    -0.06
    ስቃ
    -0.06
    েজ
    -0.06
    already
    -0.06
    POSITIVE LOGITS
     gratis
    0.06
     valuable
    0.06
     保存
    0.06
     값
    0.06
    这是一个
    0.06
    こちらも
    0.06
     personal
    0.05
     leurs
    0.05
     pessoais
    0.05
     digitale
    0.05
    Activations Density 0.001%

    No Known Activations