© 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. 119436
    Prev
    Next
    INDEX
    Explanations

    version control, identifiers

    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
     перемен
    -0.06
     singh
    -0.06
     Вин
    -0.06
    hü
    -0.06
     versus
    -0.06
    jení
    -0.06
     مشا
    -0.06
     tiba
    -0.06
    siye
    -0.06
     customization
    -0.06
    POSITIVE LOGITS
     उपरोक्त
    0.06
     betyder
    0.06
    以上
    0.06
    maxValue
    0.06
    名称
    0.06
     Arabs
    0.06
     зокрема
    0.06
     other
    0.05
     कुत्ते
    0.05
     Spartans
    0.05
    Activations Density 0.006%

    No Known Activations