© 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. 117080
    Prev
    Next
    INDEX
    Explanations

    login actions

    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
     বর্ধ
    -0.06
     சென்ன
    -0.05
    系列的
    -0.05
     бе
    -0.05
    っているので
    -0.05
    oldown
    -0.05
     brewed
    -0.05
     aumento
    -0.05
     Swezey
    -0.05
     ज्यात
    -0.05
    POSITIVE LOGITS
    PATH
    0.06
     bullied
    0.06
    质疑
    0.06
     greats
    0.06
     infinito
    0.06
     Truy
    0.06
     linking
    0.06
     있지만
    0.06
     bacter
    0.06
    জাতি
    0.06
    Activations Density 0.003%

    No Known Activations