© 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. 131051
    Prev
    Next
    INDEX
    Explanations

    code comments and headers

    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
     to
    -0.07
     след
    -0.06
    they
    -0.06
    type
    -0.06
    if
    -0.06
    eric
    -0.05
    াচ
    -0.05
    Якщо
    -0.05
     дуже
    -0.05
     if
    -0.05
    POSITIVE LOGITS
     bullied
    0.07
     café
    0.07
     protecting
    0.06
    iamy
    0.06
     রাজধানী
    0.06
     শরণার্থীরা
    0.06
     justement
    0.06
     για
    0.06
    jahteraan
    0.06
     staunch
    0.06
    Activations Density 0.002%

    No Known Activations