© 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. 129920
    Prev
    Next
    INDEX
    Explanations

    universal quantifiers

    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
     then
    -0.07
     отриму
    -0.06
    各种
    -0.06
    特に
    -0.06
     CN
    -0.06
     accepter
    -0.06
     disponibilité
    -0.06
     سپس
    -0.06
     pow
    -0.06
     ሙሉ
    -0.06
    POSITIVE LOGITS
     여기서
    0.06
     apresentação
    0.06
     flanking
    0.06
     zullen
    0.06
    这个
    0.06
     wären
    0.06
    सबसे
    0.06
     دې
    0.06
     ಹಾಗೂ
    0.06
     فائل
    0.06
    Activations Density 0.003%

    No Known Activations