© 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. 131046
    Prev
    Next
    INDEX
    Explanations

    album release dates

    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
     University
    -0.07
     dezvolt
    -0.06
    主动
    -0.06
     cran
    -0.06
     snorkel
    -0.06
    University
    -0.06
     السؤال
    -0.06
     onRequest
    -0.06
     우리나라
    -0.06
     mingling
    -0.06
    POSITIVE LOGITS
    zk
    0.07
    eit
    0.06
     specie
    0.06
    罵
    0.06
     العص
    0.05
    ASCII
    0.05
    १८
    0.05
    nodes
    0.05
    를
    0.05
    Former
    0.05
    Activations Density 0.047%

    No Known Activations