© 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. 130880
    Prev
    Next
    INDEX
    Explanations

    code keywords 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
     their
    -0.06
     cihaz
    -0.06
    លោក
    -0.06
     растений
    -0.06
     malignancy
    -0.06
     कहे
    -0.06
     მათი
    -0.05
    Transactions
    -0.05
     მისი
    -0.05
     DIE
    -0.05
    POSITIVE LOGITS
    積極的に
    0.07
    이라는
    0.06
     каких
    0.06
     أفضل
    0.06
     welchen
    0.06
     여기
    0.05
    gea
    0.05
     ज्‍यादा
    0.05
    ਦੇ
    0.05
    প্ল
    0.05
    Activations Density 0.005%

    No Known Activations