© 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. 120797
    Prev
    Next
    INDEX
    Explanations

    license specification security

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Canadi
    -0.06
     creer
    -0.06
     assigned
    -0.06
     psyched
    -0.06
    iono
    -0.06
    Images
    -0.06
     রজ
    -0.06
     ற
    -0.06
     recomenda
    -0.06
    Simulator
    -0.06
    POSITIVE LOGITS
     bietet
    0.06
     disruption
    0.06
    errno
    0.06
     innovations
    0.06
     tradicionales
    0.06
    CUSTOMER
    0.06
    ).
    0.06
     modernization
    0.06
     nowoczes
    0.05
    越高
    0.05
    Activations Density 0.004%

    No Known Activations