© 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. 119226
    Prev
    Next
    INDEX
    Explanations

    local identifiers, keywords, and punctuation

    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
    政
    -0.06
    new
    -0.06
     ans
    -0.06
    for
    -0.05
    Social
    -0.05
    /
    -0.05
    真
    -0.05
     locksmith
    -0.05
    Goal
    -0.05
    Element
    -0.05
    POSITIVE LOGITS
     가장
    0.08
     нај
    0.07
     सबसे
    0.07
     wichtigsten
    0.07
    最も
    0.07
     进行
    0.07
     ഏറ്റവും
    0.07
     naj
    0.07
    最重要的
    0.06
     kõige
    0.06
    Activations Density 0.021%

    No Known Activations