© 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. 129688
    Prev
    Next
    INDEX
    Explanations

    qualified sports coaches

    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
     Midlands
    -0.06
    oeil
    -0.06
     modest
    -0.06
     anhand
    -0.06
     Golub
    -0.06
     ®
    -0.06
    混合
    -0.05
    僅
    -0.05
     horticulture
    -0.05
    ॉर्डिंग
    -0.05
    POSITIVE LOGITS
    Uncle
    0.07
     Uncle
    0.06
    Outstanding
    0.06
     líqu
    0.06
    toler
    0.06
     तला
    0.06
     எரி
    0.06
     Oktoberfest
    0.06
    ब्र
    0.06
     toler
    0.06
    Activations Density 0.035%

    No Known Activations