© 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. 129149
    Prev
    Next
    INDEX
    Explanations

    housing, foundation, water, shelving

    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
    CardArray
    -0.06
    放到
    -0.06
     vorher
    -0.06
     thermos
    -0.06
     silently
    -0.06
     ايجاد
    -0.06
     преди
    -0.06
    usually
    -0.06
     sebelumnya
    -0.05
     previos
    -0.05
    POSITIVE LOGITS
     what
    0.06
     touches
    0.06
     फंक्शन
    0.06
    कॉम
    0.06
     sejarah
    0.06
     scrape
    0.06
     scraping
    0.06
    Feeling
    0.06
     و
    0.06
     after
    0.06
    Activations Density 0.018%

    No Known Activations