© 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. 117847
    Prev
    Next
    INDEX
    Explanations

    numerous infants

    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
    每一个
    -0.06
     Ecusson
    -0.06
     njen
    -0.06
    每一個
    -0.06
     ഒരിക്ക
    -0.06
     Если
    -0.06
     obecnie
    -0.06
     mnogo
    -0.06
     전망
    -0.06
     каждый
    -0.06
    POSITIVE LOGITS
    保护
    0.06
    বিশ্ব
    0.06
     protection
    0.06
    protection
    0.06
    에서는
    0.06
     derajat
    0.06
    สื่อ
    0.05
     then
    0.05
     permitirá
    0.05
    也将
    0.05
    Activations Density 0.001%

    No Known Activations