© 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. 120757
    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
     circumstantial
    -0.06
    Regarding
    -0.06
     overestimated
    -0.06
     regarding
    -0.06
     overestimate
    -0.06
     escalas
    -0.06
     defaulting
    -0.06
     inconclusive
    -0.06
     وسی
    -0.06
     Substitute
    -0.06
    POSITIVE LOGITS
    destructive
    0.07
     разру
    0.06
     كيفية
    0.06
    新たな
    0.06
    重量
    0.06
    ត្រ
    0.06
    adece
    0.06
     WWE
    0.06
     yık
    0.06
     ব্রহ
    0.06
    Activations Density 0.000%

    No Known Activations