© 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. 117956
    Prev
    Next
    INDEX
    Explanations

    tentative graduation dates

    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
     new
    -0.07
     сучас
    -0.06
     bree
    -0.06
     NEW
    -0.06
    ならでは
    -0.06
    新
    -0.06
     nouvelle
    -0.06
    뉴
    -0.06
     сочета
    -0.06
     newcomer
    -0.06
    POSITIVE LOGITS
     all
    0.06
     njima
    0.06
     সাপোর্ট
    0.06
     These
    0.06
     necessários
    0.06
     осуществ
    0.06
    🧗
    0.06
     initialized
    0.06
     반드시
    0.06
     frenzy
    0.06
    Activations Density 0.003%

    No Known Activations