© 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. 120390
    Prev
    Next
    INDEX
    Explanations

    allow to

    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
    直到
    -0.06
     หา
    -0.06
     Vermö
    -0.06
    particip
    -0.06
    企业的
    -0.06
    ጀመሪያ
    -0.06
    ayed
    -0.06
     Exhibits
    -0.06
     viac
    -0.05
     ='
    -0.05
    POSITIVE LOGITS
     दूसरी
    0.06
     другие
    0.06
     otro
    0.06
     अज्ञात
    0.06
     другое
    0.06
     और
    0.06
     어떤
    0.06
     allow
    0.06
     формирования
    0.06
     उत्साहित
    0.06
    Activations Density 0.001%

    No Known Activations