© 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. 128260
    Prev
    Next
    INDEX
    Explanations

    saw a

    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
     used
    -0.08
     했던
    -0.07
     했다
    -0.06
     गत
    -0.06
     belonged
    -0.06
     از
    -0.06
     it
    -0.06
     with
    -0.06
     originally
    -0.06
    avait
    -0.06
    POSITIVE LOGITS
    讓人
    0.06
     môžete
    0.06
     المنا
    0.06
     sportsmen
    0.06
     powinien
    0.06
     můžete
    0.06
     দে
    0.06
    据悉
    0.06
     압
    0.06
     anyone
    0.05
    Activations Density 0.003%

    No Known Activations