© 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. 129291
    Prev
    Next
    INDEX
    Explanations

    according to / a decade / another Prohibition

    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
     nuevas
    -0.06
     yeni
    -0.06
     নতুন
    -0.06
     новым
    -0.06
     nuevos
    -0.06
     NEW
    -0.06
     platforms
    -0.06
     الجديد
    -0.06
     represents
    -0.06
    POSITIVE LOGITS
     выполнение
    0.07
    遭受
    0.06
    📊
    0.06
    handsome
    0.06
     ребенка
    0.06
    Pure
    0.06
     Luís
    0.06
     заработной
    0.06
     alemán
    0.06
    kenny
    0.06
    Activations Density 0.008%

    No Known Activations