© 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. 130188
    Prev
    Next
    INDEX
    Explanations

    sports teams and cities

    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
     просмо
    -0.07
     spezi
    -0.07
     demost
    -0.06
     zahlreichen
    -0.06
    Spatial
    -0.06
     sogenannten
    -0.06
     dimost
    -0.06
    Again
    -0.06
     সেসব
    -0.06
     query
    -0.06
    POSITIVE LOGITS
    ResourceManager
    0.06
    /(
    0.06
    ighed
    0.06
    '][$
    0.05
     inbound
    0.05
     precedents
    0.05
     reprieve
    0.05
     entrer
    0.05
     rallied
    0.05
    wości
    0.05
    Activations Density 0.013%

    No Known Activations