© 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. 116048
    Prev
    Next
    INDEX
    Explanations

    derivative definitions

    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
    ໋
    -0.07
     آماده
    -0.07
    ോട്
    -0.06
    ्यावर
    -0.06
    okolade
    -0.06
    ώσεις
    -0.06
    న్నా
    -0.06
     később
    -0.06
     💪
    -0.06
    Ņ
    -0.06
    POSITIVE LOGITS
    (/^
    0.06
    κτη
    0.06
     ลํา
    0.05
     ở
    0.05
    its
    0.05
     huit
    0.05
    az
    0.05
     그
    0.05
     C
    0.05
    在
    0.05
    Activations Density 0.002%

    No Known Activations