© 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. 118496
    Prev
    Next
    INDEX
    Explanations

    code imports and declarations

    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
     langsung
    -0.06
    いただいた
    -0.06
     cope
    -0.06
     lahat
    -0.06
    ಲಾಯಿತು
    -0.06
     kill
    -0.06
    🍰
    -0.06
     vš
    -0.06
     받았
    -0.06
     give
    -0.06
    POSITIVE LOGITS
    feat
    0.07
     campsite
    0.06
    可在
    0.06
     कर्तव्य
    0.06
     Zero
    0.06
     NFT
    0.06
     PFAS
    0.06
     cStart
    0.06
     प्रतिभाग
    0.06
    
    0.06
    Activations Density 0.002%

    No Known Activations