© 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. 130438
    Prev
    Next
    INDEX
    Explanations

    reply to posts

    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
     Business
    -0.06
     Horticultural
    -0.06
    Business
    -0.06
     northwestern
    -0.06
     niego
    -0.06
     المعادلات
    -0.06
     бизнес
    -0.06
     equivalently
    -0.06
    农
    -0.06
     trabalhando
    -0.06
    POSITIVE LOGITS
     स्थानीय
    0.07
     reply
    0.06
     responses
    0.06
     dalam
    0.06
     рекоменда
    0.06
     within
    0.06
     ಸ್ಥಳ
    0.06
     বংশ
    0.06
    有助于
    0.06
    氛
    0.06
    Activations Density 0.009%

    No Known Activations