© 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. 129590
    Prev
    Next
    INDEX
    Explanations

    sports and professional activities

    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
     ибо
    -0.07
     الكبير
    -0.06
     foolish
    -0.06
     usb
    -0.06
     or
    -0.06
     spus
    -0.06
     diye
    -0.06
     for
    -0.06
    Navigation
    -0.06
     ritorno
    -0.06
    POSITIVE LOGITS
     עם
    0.07
     upcoming
    0.06
     afgelopen
    0.06
     হত্যাকা
    0.06
    num
    0.06
     Nevertheless
    0.06
     खासदार
    0.06
    ;
    0.06
    لسل
    0.06
     অধিকাংশ
    0.06
    Activations Density 0.043%

    No Known Activations