© 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. 129936
    Prev
    Next
    INDEX
    Explanations

    during fabrication, byte, field of

    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
    躺
    -0.06
     comparing
    -0.06
    を確認
    -0.06
     comparar
    -0.06
    गैर
    -0.06
     specific
    -0.06
    )'
    -0.06
    それぞれの
    -0.06
     instalado
    -0.06
    ander
    -0.06
    POSITIVE LOGITS
    getSimpleName
    0.06
     perpetually
    0.06
     nikdy
    0.06
    setVisibility
    0.06
    acios
    0.06
     ગામ
    0.06
     ALWAYS
    0.06
    ◊
    0.06
     visor
    0.06
    ચા
    0.06
    Activations Density 0.004%

    No Known Activations