© 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. 118447
    Prev
    Next
    INDEX
    Explanations

    test command snippets

    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
     secondly
    -0.06
     دوسرا
    -0.06
     নানা
    -0.06
     ďal
    -0.05
    第二
    -0.05
    siehe
    -0.05
     outras
    -0.05
     કેટલી
    -0.05
    сіі
    -0.05
    _;
    -0.05
    POSITIVE LOGITS
    Represent
    0.07
     representation
    0.06
    表示
    0.06
    ₮
    0.06
    标记
    0.06
    While
    0.06
     höheren
    0.06
    Copies
    0.06
     තුළ
    0.06
     suaves
    0.06
    Activations Density 0.002%

    No Known Activations