© 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. 117217
    Prev
    Next
    INDEX
    Explanations

    web services requests

    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
    ոլ
    -0.06
    史
    -0.06
     도시
    -0.06
     नियामक
    -0.06
     Regulatory
    -0.06
    ถนน
    -0.06
     적용
    -0.06
     প্রত্যেক
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
     social
    -0.05
    POSITIVE LOGITS
     Frey
    0.07
    SGD
    0.06
     agreements
    0.06
     watercolour
    0.06
     Takahashi
    0.06
     Parkinson
    0.06
     आस्ट्रेलिया
    0.06
    を守
    0.06
     webpage
    0.06
     охра
    0.06
    Activations Density 0.009%

    No Known Activations