© 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. 128427
    Prev
    Next
    INDEX
    Explanations

    API levels and versions

    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
     രണ്ടു
    -0.06
     zuerst
    -0.06
    ilebilir
    -0.06
     مقامی
    -0.06
     முதலில்
    -0.06
    數位
    -0.06
    serif
    -0.06
    ानीय
    -0.06
     цифро
    -0.06
     cellphone
    -0.06
    POSITIVE LOGITS
     аналоги
    0.07
     an
    0.07
     অনুরূপ
    0.07
     simil
    0.06
     similar
    0.06
    相似
    0.06
     similarly
    0.06
     stripped
    0.06
     مشابه
    0.06
    様の
    0.06
    Activations Density 0.001%

    No Known Activations