© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118499
    Prev
    Next
    INDEX
    Explanations

    ajax calls

    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
     û
    -0.06
     sort
    -0.06
     փ
    -0.06
     salve
    -0.06
    beyond
    -0.06
    虽然
    -0.06
     bin
    -0.06
     această
    -0.06
    println
    -0.05
     deles
    -0.05
    POSITIVE LOGITS
     the
    0.07
     ergonomic
    0.07
     ultime
    0.06
     Buddhists
    0.06
     शास्त्रों
    0.06
     jabatan
    0.06
    ammable
    0.06
     वो
    0.06
     consejo
    0.06
     ceinture
    0.06
    Activations Density 0.007%

    No Known Activations