© 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. 130452
    Prev
    Next
    INDEX
    Explanations

    specific programming language constructs

    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
    Quando
    -0.07
     Obwohl
    -0.07
     testers
    -0.07
     quando
    -0.07
     testing
    -0.07
    测试
    -0.07
     cuando
    -0.07
    後
    -0.06
     niemals
    -0.06
    courts
    -0.06
    POSITIVE LOGITS
     from
    0.08
     từ
    0.07
    から
    0.06
    からの
    0.06
    于是
    0.06
     specific
    0.06
     συγκεκρι
    0.06
     on
    0.06
     level
    0.06
     PARTICULAR
    0.06
    Activations Density 0.002%

    No Known Activations