© 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. 130499
    Prev
    Next
    INDEX
    Explanations

    one of [number/determiner/quantifier]

    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
    titled
    -0.07
     if
    -0.07
     the
    -0.06
     titled
    -0.06
     your
    -0.06
     one
    -0.06
     iconic
    -0.06
     If
    -0.06
     exporting
    -0.06
     where
    -0.06
    POSITIVE LOGITS
     эту
    0.07
     полностью
    0.07
    これらの
    0.07
     эти
    0.07
     шесть
    0.07
     drei
    0.06
     первые
    0.06
     ۱۵
    0.06
    Hundreds
    0.06
     Hundreds
    0.06
    Activations Density 0.010%

    No Known Activations