© 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. 118318
    Prev
    Next
    INDEX
    Explanations

    stimulus bills and large sums of money

    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
     intensifying
    -0.07
     বিগত
    -0.06
     debilitating
    -0.06
     систему
    -0.06
    year
    -0.06
     ruin
    -0.06
     your
    -0.06
     હિ
    -0.06
    今年
    -0.06
    🐧
    -0.06
    POSITIVE LOGITS
     내용
    0.06
     для
    0.06
     내용은
    0.06
    ambarkan
    0.06
    اة
    0.06
     विकास
    0.06
    impan
    0.06
    ptitle
    0.06
    President
    0.05
    當中
    0.05
    Activations Density 0.007%

    No Known Activations