© 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. 128176
    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
     to
    -0.07
    因为它
    -0.07
     by
    -0.06
    它是
    -0.06
    4
    -0.06
    Figs
    -0.06
     दिखाकर
    -0.05
    把
    -0.05
    ys
    -0.05
    的人物
    -0.05
    POSITIVE LOGITS
    potentially
    0.07
     potentially
    0.07
     সম্ভাব্য
    0.07
     সঠিক
    0.07
     نفسی
    0.07
    🥺
    0.06
    xcuser
    0.06
    ☺️
    0.06
     deceived
    0.06
    ffine
    0.06
    Activations Density 0.000%

    No Known Activations