© 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. 130563
    Prev
    Next
    INDEX
    Explanations

    window, time, algorithm, code

    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
    上
    -0.06
    额
    -0.06
     estimation
    -0.06
     ধরেই
    -0.06
    estimates
    -0.06
     respecto
    -0.05
     पैनल
    -0.05
    맬
    -0.05
     suivant
    -0.05
    基
    -0.05
    POSITIVE LOGITS
    に必要な
    0.07
    فات
    0.06
    폄
    0.06
     READ
    0.06
     botão
    0.06
     позволя
    0.06
     इन्वेस्टमेंट
    0.06
     έκ
    0.06
     full
    0.06
     Taste
    0.06
    Activations Density 0.011%

    No Known Activations