© 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. 120802
    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
     ώ
    -0.06
     находятся
    -0.06
     Utilisez
    -0.06
     portant
    -0.06
     wannan
    -0.05
     vannak
    -0.05
     Rapp
    -0.05
    ͂
    -0.05
     deplorable
    -0.05
    ゛
    -0.05
    POSITIVE LOGITS
     change
    0.06
     would
    0.06
    ），
    0.06
     nari
    0.06
     Change
    0.06
    autre
    0.06
     along
    0.06
     tých
    0.06
     तब
    0.06
    ሎችን
    0.06
    Activations Density 0.000%

    No Known Activations