© 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. 130345
    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
    去
    -0.07
     prevista
    -0.06
     going
    -0.06
     পেছন
    -0.06
    masının
    -0.06
     бү
    -0.06
    誕生
    -0.06
    expected
    -0.06
     восстанов
    -0.06
     probably
    -0.06
    POSITIVE LOGITS
     nigh
    0.06
     desirable
    0.06
     onze
    0.06
     正
    0.06
    ivalent
    0.06
    相反
    0.05
    тинен
    0.05
     তাৎ
    0.05
    إذا
    0.05
    番組
    0.05
    Activations Density 0.000%

    No Known Activations