© 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. 129875
    Prev
    Next
    INDEX
    Explanations

    shop-in-shop

    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
     ſ
    -0.07
     extraordinarily
    -0.06
    其中的
    -0.06
     quei
    -0.06
     those
    -0.06
    來的
    -0.06
     फक्त
    -0.06
    たちは
    -0.06
    !!!!!
    -0.06
    こちらは
    -0.06
    POSITIVE LOGITS
     for
    0.07
     by
    0.07
     as
    0.07
    を
    0.06
     at
    0.06
    作为
    0.06
    ன்னை
    0.06
     the
    0.06
     великолеп
    0.06
     ระยะ
    0.06
    Activations Density 0.024%

    No Known Activations