© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131002
    Prev
    Next
    INDEX
    Explanations

    code tags and symbols

    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
     Medicines
    -0.06
    再加上
    -0.06
    اته
    -0.06
     آینده
    -0.06
     그리고
    -0.06
     тво
    -0.06
     మంచి
    -0.06
     স্থানের
    -0.05
    れば
    -0.05
    ቸ
    -0.05
    POSITIVE LOGITS
    *,
    0.06
    Coroutine
    0.06
     (*
    0.06
     (\"
    0.06
     gyors
    0.06
    storm
    0.06
     García
    0.06
    hort
    0.06
     Band
    0.06
     確認
    0.06
    Activations Density 0.001%

    No Known Activations