© 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. 128180
    Prev
    Next
    INDEX
    Explanations

    now, already, soon

    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
    现有
    -0.07
     Uganda
    -0.07
     governo
    -0.07
    彊
    -0.06
     mevcut
    -0.06
     جمهوری
    -0.06
     মেরে
    -0.06
     lessons
    -0.06
     ພວກເຮົາ
    -0.06
     луч
    -0.06
    POSITIVE LOGITS
     이제
    0.07
    이제
    0.06
    yní
    0.06
     now
    0.06
    Ahora
    0.06
    Теперь
    0.06
    azia
    0.06
     désormais
    0.06
     теперь
    0.05
    now
    0.05
    Activations Density 0.073%

    No Known Activations