© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130055
    Prev
    Next
    INDEX
    Explanations

    mathematical questions

    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
     Tregs
    -0.07
     dibanding
    -0.06
                   
    -0.06
    nan
    -0.06
     compat
    -0.06
    షన్‌
    -0.06
    複数
    -0.06
     spezif
    -0.06
    Từ
    -0.06
    multif
    -0.06
    POSITIVE LOGITS
    今日も
    0.06
    ☆
    0.06
     ضلع
    0.06
    holy
    0.06
     thyme
    0.06
     μαγγ
    0.06
    学
    0.05
    anyone
    0.05
     repurposed
    0.05
     ئەو
    0.05
    Activations Density 0.001%

    No Known Activations