© 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. 130673
    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
    exec
    -0.06
     গণতন্ত্র
    -0.06
     今
    -0.06
     Reason
    -0.06
     এবার
    -0.05
     accordingly
    -0.05
    -0.05
     فیصلہ
    -0.05
    Está
    -0.05
    eb
    -0.05
    POSITIVE LOGITS
    against
    0.07
     ಮತ್ತು
    0.07
     against
    0.07
     ಸಾಮಾನ್ಯ
    0.07
     ਅਤੇ
    0.07
     सामान्य
    0.07
     cualquier
    0.06
     primeira
    0.06
    otros
    0.06
     obligación
    0.06
    Activations Density 0.000%

    No Known Activations