© 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. 116219
    Prev
    Next
    INDEX
    Explanations

    #include <linux>

    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
     до
    -0.07
     из
    -0.07
     на
    -0.07
    などは
    -0.06
    За
    -0.06
    Coff
    -0.06
     какой
    -0.06
     proš
    -0.06
    کنندگان
    -0.06
     два
    -0.06
    POSITIVE LOGITS
     heartbreaking
    0.07
     alluring
    0.07
     lapin
    0.06
     dogged
    0.06
     impair
    0.06
     Dispon
    0.06
     الشيء
    0.06
    pesar
    0.06
     approximated
    0.06
     प्यार
    0.06
    Activations Density 0.001%

    No Known Activations