© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116804
    Prev
    Next
    INDEX
    Explanations

    net worth and financial figures

    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
     يريد
    -0.07
     الجديدة
    -0.06
     नया
    -0.06
     모든
    -0.06
     desiring
    -0.06
     нового
    -0.06
     consensual
    -0.06
     सभी
    -0.06
     herkese
    -0.06
     nowego
    -0.06
    POSITIVE LOGITS
     estimated
    0.07
     estimate
    0.07
    estimated
    0.07
    ประมาณ
    0.07
    估计
    0.07
     estimado
    0.07
    每年
    0.06
    在庫
    0.06
     battaglia
    0.06
     अनुमान
    0.06
    Activations Density 0.006%

    No Known Activations