© 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. 115963
    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
     이는
    -0.07
     using
    -0.07
     use
    -0.07
     소련
    -0.06
    irled
    -0.06
     மற்றொரு
    -0.06
     της
    -0.06
     pricing
    -0.06
     গানের
    -0.06
     trái
    -0.06
    POSITIVE LOGITS
     notification
    0.07
     notific
    0.07
     burdensome
    0.07
     revêt
    0.06
     hayat
    0.06
     glossy
    0.06
     ජී
    0.06
     autoload
    0.06
     informational
    0.06
     escort
    0.06
    Activations Density 0.000%

    No Known Activations