© 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. 128942
    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
     balans
    -0.07
     кожи
    -0.06
    imary
    -0.06
    大きな
    -0.06
     دیگر
    -0.06
    捌
    -0.05
    首先
    -0.05
    和其他
    -0.05
     مسائل
    -0.05
     अन्य
    -0.05
    POSITIVE LOGITS
     time
    0.11
    時間
    0.09
    时间
    0.09
     timed
    0.09
     thời
    0.09
    time
    0.08
    的時間
    0.07
     Duration
    0.07
     Time
    0.07
     duration
    0.07
    Activations Density 0.000%

    No Known Activations