© 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. 130064
    Prev
    Next
    INDEX
    Explanations

    lists of numbers, roles, or queries

    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
     davantage
    -0.06
     जितने
    -0.06
     हजारों
    -0.06
     captives
    -0.06
    َن
    -0.06
     Thousands
    -0.06
    trifluoromethyl
    -0.06
     सपने
    -0.05
     Bursa
    -0.05
     will
    -0.05
    POSITIVE LOGITS
    तों
    0.07
     አንዳንድ
    0.07
     distância
    0.07
     некоторые
    0.06
     külön
    0.06
     особо
    0.06
    itism
    0.06
     தவிர்க்க
    0.06
    特别
    0.06
     various
    0.06
    Activations Density 0.001%

    No Known Activations