© 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. 117408
    Prev
    Next
    INDEX
    Explanations

    numbers or geographical locations followed by names

    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
     この
    -0.07
     這個
    -0.06
     التي
    -0.06
    ឬ
    -0.06
     Most
    -0.06
    對
    -0.06
     这个
    -0.06
    Most
    -0.06
    ździe
    -0.06
     usw
    -0.06
    POSITIVE LOGITS
    aas
    0.06
    hos
    0.06
    দীর্ঘ
    0.06
    ɩ
    0.06
    是一位
    0.06
     اکتوبر
    0.06
     MAC
    0.05
    мах
    0.05
     länger
    0.05
     अध्यक्ष
    0.05
    Activations Density 0.002%

    No Known Activations