© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130964
    Prev
    Next
    INDEX
    Explanations

    color or colours

    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
     facilita
    -0.07
    opcode
    -0.06
    FieldValue
    -0.06
     初
    -0.06
     Begriff
    -0.06
     небе
    -0.06
    ỳnh
    -0.06
     facilitar
    -0.06
     eğitimi
    -0.06
     মাটিতে
    -0.06
    POSITIVE LOGITS
     which
    0.06
    Which
    0.06
     fashion
    0.06
    Wait
    0.06
    Art
    0.06
     vignette
    0.06
     wait
    0.05
    恫
    0.05
     there
    0.05
    imsy
    0.05
    Activations Density 0.005%

    No Known Activations