© 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. 118128
    Prev
    Next
    INDEX
    Explanations

    location, climate, weather

    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
    components
    -0.07
     화면
    -0.06
     भेदभाव
    -0.06
     discomfort
    -0.06
    Component
    -0.05
     прикла
    -0.05
    volence
    -0.05
    lemente
    -0.05
    extreme
    -0.05
    म्प्ट
    -0.05
    POSITIVE LOGITS
    ✚
    0.06
     ප්‍රති
    0.06
    ूबी
    0.06
     Approved
    0.06
     이유
    0.06
     rendszer
    0.06
     বাড়ির
    0.06
    等级
    0.06
     standard
    0.06
     હંમે
    0.06
    Activations Density 0.019%

    No Known Activations