© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 115943
    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
    Negative Logits
     वास्तविक
    -0.08
     ತಮ್ಮ
    -0.07
    Programm
    -0.06
    temuan
    -0.06
     своїх
    -0.06
    真是
    -0.06
    Absolutely
    -0.06
     сообщи
    -0.06
     absolutely
    -0.06
     svojih
    -0.06
    POSITIVE LOGITS
     F
    0.07
     GP
    0.06
    ,
    0.06
    然后
    0.06
    云
    0.06
    一方で
    0.06
    ike
    0.06
    <em>
    0.06
    跟
    0.06
    ."
    0.05
    Activations Density 0.000%

    No Known Activations