© 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. 130812
    Prev
    Next
    INDEX
    Explanations

    file writing

    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
     Bisch
    -0.07
     শুনানি
    -0.07
     kalor
    -0.06
    𝗧
    -0.06
     exibir
    -0.06
    перыі
    -0.06
     Art
    -0.06
     showcase
    -0.06
    ავი
    -0.06
    Kyr
    -0.06
    POSITIVE LOGITS
    crew
    0.07
    和我
    0.06
    slack
    0.06
     подготовке
    0.06
    跟我
    0.06
    〔
    0.06
    徹底
    0.06
     totaal
    0.06
     that
    0.05
    simplex
    0.05
    Activations Density 0.005%

    No Known Activations