© 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. 128919
    Prev
    Next
    INDEX
    Explanations

    US state names followed by teams or elections

    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
     mencoba
    -0.06
    ่า
    -0.06
     försö
    -0.06
     الصفحه
    -0.05
     prey
    -0.05
     ancestral
    -0.05
    ждения
    -0.05
    écie
    -0.05
     Monsieur
    -0.05
     Estimated
    -0.05
    POSITIVE LOGITS
     riserv
    0.06
     dekat
    0.06
     nominations
    0.06
     совершенно
    0.06
     which
    0.06
     Quando
    0.06
    不管是
    0.06
     quando
    0.06
     अवार्ड
    0.06
     GaAs
    0.06
    Activations Density 0.017%

    No Known Activations