© 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. 128751
    Prev
    Next
    INDEX
    Explanations

    dates and specific nouns

    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
     shareholder
    -0.06
     स्मार्टफोन
    -0.06
     shareholders
    -0.06
     patiently
    -0.06
    Петербург
    -0.06
     intérêt
    -0.06
     interes
    -0.06
    独特的
    -0.06
     acab
    -0.06
     left
    -0.06
    POSITIVE LOGITS
    cuda
    0.06
     multe
    0.06
     birçok
    0.06
     많은
    0.06
    avoir
    0.06
     wielu
    0.06
     vielen
    0.05
    many
    0.05
     cortex
    0.05
     many
    0.05
    Activations Density 0.001%

    No Known Activations