© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116985
    Prev
    Next
    INDEX
    Explanations

    64-bit

    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
    而是
    -0.06
     যু
    -0.06
     matière
    -0.06
    अनि
    -0.06
    纳米
    -0.06
     Kal
    -0.06
     getting
    -0.06
    ഷ്‌
    -0.06
     вместо
    -0.05
    美
    -0.05
    POSITIVE LOGITS
     although
    0.07
     distribuição
    0.06
     सोम
    0.06
    Foto
    0.06
     Behold
    0.06
    жению
    0.06
     distribución
    0.06
     "",
    0.06
     उंची
    0.06
     alcuna
    0.06
    Activations Density 0.005%

    No Known Activations