© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118372
    Prev
    Next
    INDEX
    Explanations

    new or recent releases

    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
     when
    -0.09
     όταν
    -0.08
    when
    -0.07
     cuando
    -0.06
     whenever
    -0.06
     quando
    -0.06
    whenever
    -0.06
     когда
    -0.06
     khi
    -0.06
     their
    -0.06
    POSITIVE LOGITS
     nuevos
    0.08
     new
    0.07
     nuove
    0.07
     новой
    0.07
     νέα
    0.07
     neue
    0.07
     новые
    0.07
     nuevas
    0.07
     nueva
    0.07
     neuen
    0.07
    Activations Density 0.028%

    No Known Activations