© 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. 119469
    Prev
    Next
    INDEX
    Explanations

    software license and legal text

    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
    ෝ
    -0.06
     Dubois
    -0.06
     probably
    -0.05
    基本
    -0.05
     Elim
    -0.05
     get
    -0.05
     refuses
    -0.05
    ӓ
    -0.05
    kak
    -0.05
     prawdopod
    -0.05
    POSITIVE LOGITS
    視覺
    0.07
     зовніш
    0.07
     музы
    0.06
    Instead
    0.06
     λόγω
    0.06
     вместо
    0.06
     invece
    0.06
    に対し
    0.06
    ஜன்
    0.06
    另一方面
    0.06
    Activations Density 0.002%

    No Known Activations