© 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. 121062
    Prev
    Next
    INDEX
    Explanations

    following code comments

    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
    Negative Logits
     относительно
    -0.06
     relatively
    -0.06
     كما
    -0.06
    optical
    -0.06
     আনু
    -0.06
    relatively
    -0.06
     Relatively
    -0.06
     relativamente
    -0.05
     geliş
    -0.05
    較
    -0.05
    POSITIVE LOGITS
    二十
    0.07
     vì
    0.06
     fordi
    0.06
     này
    0.06
     listas
    0.06
    この
    0.06
    每一個
    0.06
    ImageList
    0.06
     براي
    0.06
     jednego
    0.06
    Activations Density 0.003%

    No Known Activations