© 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. 130986
    Prev
    Next
    INDEX
    Explanations

    lists of items or concepts

    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
     strikingly
    -0.07
    类似的
    -0.07
     fabulous
    -0.07
     पॉजिटिव
    -0.07
     supremely
    -0.07
     marvelous
    -0.06
    orgeous
    -0.06
     professors
    -0.06
     mesmerizing
    -0.06
     zatim
    -0.06
    POSITIVE LOGITS
    我們的
    0.06
     nostri
    0.06
     our
    0.06
    풀
    0.06
    our
    0.06
    ification
    0.06
     ukuran
    0.06
     Unsere
    0.06
     nær
    0.05
     Our
    0.05
    Activations Density 0.040%

    No Known Activations