© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120514
    Prev
    Next
    INDEX
    Explanations

    seeing, watching, happening

    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
     would
    -0.07
     Buen
    -0.07
    zedł
    -0.06
     tels
    -0.06
     знает
    -0.06
    什么
    -0.06
     понял
    -0.06
     unleashed
    -0.06
     foliis
    -0.06
     രണ്ട്
    -0.06
    POSITIVE LOGITS
     そして
    0.06
    たっぷ
    0.06
     هنگام
    0.06
    🟠
    0.06
    ･
    0.06
    Therefore
    0.06
     Spagna
    0.06
    時
    0.06
     gorgeous
    0.06
     exquisite
    0.06
    Activations Density 0.045%

    No Known Activations