© 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. 130667
    Prev
    Next
    INDEX
    Explanations

    STATE ex rel

    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
     local
    -0.08
    当地
    -0.07
     lokale
    -0.07
    local
    -0.06
     мест
    -0.06
     locais
    -0.06
     местные
    -0.06
     λόγω
    -0.05
     स्थानीय
    -0.05
    aried
    -0.05
    POSITIVE LOGITS
     Confidence
    0.06
    وف
    0.06
     разработки
    0.06
     sovereigns
    0.06
     trono
    0.06
     tó
    0.06
    ofi
    0.06
    ब्रु
    0.06
     peso
    0.06
    orrow
    0.06
    Activations Density 0.011%

    No Known Activations