© 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. 128284
    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
     designed
    -0.06
     necessary
    -0.06
    ())->
    -0.06
    🌀
    -0.06
    dfs
    -0.05
     जलाश
    -0.05
     প্রত্যেকের
    -0.05
    
    -0.05
    design
    -0.05
    iad
    -0.05
    POSITIVE LOGITS
     также
    0.08
     نیز
    0.07
     может
    0.07
     ਵੀ
    0.07
    或許
    0.07
     também
    0.07
     شاید
    0.07
     también
    0.07
     связи
    0.07
     همچنین
    0.07
    Activations Density 0.000%

    No Known Activations