© 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. 130612
    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
     include
    -0.08
     luôn
    -0.07
     includes
    -0.07
     always
    -0.06
     শুধুমাত্র
    -0.06
    回家
    -0.06
     รวม
    -0.06
    includes
    -0.06
     for
    -0.06
    Includes
    -0.06
    POSITIVE LOGITS
     बम
    0.06
     이어
    0.06
     sebagai
    0.06
    系の
    0.06
    悩み
    0.06
     crores
    0.06
    TableView
    0.06
    釀
    0.06
     ২০০
    0.05
    consciousness
    0.05
    Activations Density 0.000%

    No Known Activations