© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117811
    Prev
    Next
    INDEX
    Explanations

    P-type semiconductor, CMOS, dates

    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
     Apparel
    -0.06
     celui
    -0.06
     mixers
    -0.06
     outfielder
    -0.06
    すごく
    -0.06
     southeast
    -0.05
     şöyle
    -0.05
     жидкости
    -0.05
    kz
    -0.05
     index
    -0.05
    POSITIVE LOGITS
     மேலே
    0.08
     retracted
    0.06
    Nickel
    0.06
     распо
    0.06
    мот
    0.06
     розта
    0.06
    لاه
    0.06
     shrank
    0.06
     rosy
    0.06
    Result
    0.06
    Activations Density 0.001%

    No Known Activations