© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130863
    Prev
    Next
    INDEX
    Explanations

    reviews, comments, concerns

    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
     advertised
    -0.06
     chiropractor
    -0.06
    实在
    -0.06
     catalytic
    -0.06
     конди
    -0.06
     neka
    -0.06
    䛛
    -0.06
     lângă
    -0.06
     rost
    -0.05
    遇到了
    -0.05
    POSITIVE LOGITS
     रिवाइज
    0.06
     कमजोरी
    0.06
     सबै
    0.06
    suggest
    0.06
    ∃
    0.06
     istnieje
    0.06
    鳩
    0.06
    ↵↵↵
    0.06
     concerns
    0.06
     органі
    0.06
    Activations Density 0.003%

    No Known Activations