© 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. 117600
    Prev
    Next
    INDEX
    Explanations

    genes, oxygen, species, pv, mapping

    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
     transporting
    -0.08
     използ
    -0.06
     utilisée
    -0.06
     transportation
    -0.06
     transport
    -0.06
     použ
    -0.06
     insulating
    -0.06
     транспорта
    -0.06
     carro
    -0.06
     shuttle
    -0.06
    POSITIVE LOGITS
     a
    0.06
     testing
    0.06
     fabricants
    0.06
     Victorian
    0.06
     contre
    0.06
     pointy
    0.06
     revenge
    0.06
     Manufacturers
    0.06
     Testing
    0.06
     катастро
    0.06
    Activations Density 0.002%

    No Known Activations