© 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. 120900
    Prev
    Next
    INDEX
    Explanations

    day and night

    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
     had
    -0.07
     mencoba
    -0.07
     ſ
    -0.06
     completed
    -0.06
     a
    -0.06
     使用
    -0.06
    .(
    -0.06
     providing
    -0.06
    Proof
    -0.06
     ※
    -0.06
    POSITIVE LOGITS
     якобы
    0.06
     while
    0.06
     пока
    0.06
     เปลี่ยน
    0.06
     semble
    0.06
    近く
    0.06
     dunque
    0.06
     scheint
    0.06
     seems
    0.06
     cambiare
    0.06
    Activations Density 0.001%

    No Known Activations