© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 127994
    Prev
    Next
    INDEX
    Explanations

    Question starters and specific words

    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
    Negative Logits
    可以用
    -0.06
     与
    -0.06
    不懂
    -0.06
     mynd
    -0.06
    だって
    -0.06
     Magellan
    -0.06
    觉得
    -0.05
    与
    -0.05
     मनात
    -0.05
    新宿
    -0.05
    POSITIVE LOGITS
     dalam
    0.08
     zarówno
    0.07
     বেশ
    0.07
     në
    0.07
     пробле
    0.06
    かなり
    0.06
     sowohl
    0.06
    oló
    0.06
    icky
    0.06
     ทั้ง
    0.06
    Activations Density 0.001%

    No Known Activations