© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129511
    Prev
    Next
    INDEX
    Explanations

    new business, features, processors

    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
     가서
    -0.08
    新
    -0.07
     qualquer
    -0.07
     cualquier
    -0.07
     nowego
    -0.07
    任何
    -0.07
    មុ
    -0.07
     各
    -0.06
    各个
    -0.06
     herhangi
    -0.06
    POSITIVE LOGITS
     used
    0.06
     taking
    0.06
     use
    0.06
     Excelente
    0.06
     more
    0.06
     यूज
    0.06
     support
    0.06
     maintaining
    0.05
     குழந்த
    0.05
    ILL
    0.05
    Activations Density 0.016%

    No Known Activations