© 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. 128835
    Prev
    Next
    INDEX
    Explanations

    CII GUI Architecture

    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
     Особенно
    -0.08
     Especially
    -0.08
    Especially
    -0.07
     особенно
    -0.06
    High
    -0.06
     Aut
    -0.06
     וב
    -0.06
     높은
    -0.06
     également
    -0.06
     especially
    -0.06
    POSITIVE LOGITS
    你
    0.07
     環境
    0.06
     gebruik
    0.06
     isother
    0.06
     நூற்ற
    0.06
     interconnect
    0.06
     يونيو
    0.06
     desist
    0.06
     جون
    0.06
     فبراير
    0.06
    Activations Density 0.015%

    No Known Activations