© 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. 117746
    Prev
    Next
    INDEX
    Explanations

    until now, then

    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
    ถ้า
    -0.06
     здесь
    -0.06
     మద్య
    -0.06
    posium
    -0.06
     seven
    -0.06
     six
    -0.06
    agree
    -0.06
     принять
    -0.06
     шесть
    -0.06
    有一个
    -0.06
    POSITIVE LOGITS
     hitherto
    0.07
     разных
    0.07
     practically
    0.06
     будущего
    0.06
    を実現
    0.06
     varias
    0.06
     ensuing
    0.06
     furthermore
    0.06
     Furthermore
    0.06
     múltipl
    0.06
    Activations Density 0.319%

    No Known Activations