© 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. 118043
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     변화
    -0.08
     تغییر
    -0.07
     Bereich
    -0.06
     perubahan
    -0.06
     کشور
    -0.06
     surrounding
    -0.06
    變化
    -0.06
    案内
    -0.06
     mga
    -0.06
     изменение
    -0.06
    POSITIVE LOGITS
     उतनी
    0.06
    Property
    0.06
     unspecified
    0.06
     CLIENT
    0.06
     first
    0.06
     calculation
    0.06
    相当
    0.06
    婚姻
    0.06
    র্ডার
    0.06
    chandelier
    0.06
    Activations Density 0.000%

    No Known Activations