© 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. 117220
    Prev
    Next
    INDEX
    Explanations

    Cheka

    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
     classics
    -0.07
    格納
    -0.06
    ProductID
    -0.06
     parliament
    -0.06
     muffler
    -0.06
     sharpen
    -0.06
     içerisinde
    -0.06
    လာ
    -0.06
     sisält
    -0.06
     encyclopedia
    -0.06
    POSITIVE LOGITS
     before
    0.06
     क्यूब
    0.06
    kak
    0.06
     Vũ
    0.06
     येलो
    0.05
     Ethereum
    0.05
    报错
    0.05
    重庆
    0.05
     botched
    0.05
    ưới
    0.05
    Activations Density 0.002%

    No Known Activations