© 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. 118801
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
     currently
    -0.07
     pengendalian
    -0.06
     জানেন
    -0.06
    lasses
    -0.06
     gaping
    -0.06
     cierta
    -0.06
     bila
    -0.06
     प्राथमिक
    -0.06
     ప్ర
    -0.06
     bepaalde
    -0.06
    POSITIVE LOGITS
     dazzling
    0.06
     Dazu
    0.06
    diversity
    0.06
     serves
    0.06
     或者
    0.06
    Sehr
    0.06
     beeindruck
    0.06
     ekki
    0.06
     both
    0.06
     他们
    0.06
    Activations Density 0.002%

    No Known Activations