© 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. 128753
    Prev
    Next
    INDEX
    Explanations

    DLL and library conflicts

    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
     Becky
    -0.06
     trắng
    -0.06
     Vaccines
    -0.06
    7
    -0.06
     светло
    -0.06
    工作的
    -0.05
    2
    -0.05
     tehn
    -0.05
     آگے
    -0.05
     позволяет
    -0.05
    POSITIVE LOGITS
     recentes
    0.07
     některé
    0.06
     excessively
    0.06
     různých
    0.06
    एमसी
    0.06
     Recent
    0.06
     różne
    0.06
     різні
    0.06
     display
    0.06
     basicamente
    0.06
    Activations Density 0.002%

    No Known Activations