© 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. 120520
    Prev
    Next
    INDEX
    Explanations

    code definition and calls

    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
     frecuentes
    -0.07
     vários
    -0.07
    şu
    -0.06
    長的
    -0.06
     работают
    -0.06
     várias
    -0.06
    常见的
    -0.06
     ,[
    -0.06
    essages
    -0.06
     eenvoud
    -0.06
    POSITIVE LOGITS
    -
    0.06
     эпо
    0.06
     spokes
    0.06
     ভূ
    0.06
     varsa
    0.06
     לאחר
    0.06
     من
    0.05
     ถ้า
    0.05
     rediscover
    0.05
     genauso
    0.05
    Activations Density 0.004%

    No Known Activations