© 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. 115830
    Prev
    Next
    INDEX
    Explanations

    clients or Client

    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
    पिंग
    -0.06
    මාණය
    -0.06
     flaky
    -0.06
     lotta
    -0.06
     Wexford
    -0.05
     decisione
    -0.05
    uvad
    -0.05
     aktiviert
    -0.05
    aktif
    -0.05
     armado
    -0.05
    POSITIVE LOGITS
     производ
    0.07
     שא
    0.07
     свою
    0.06
     otros
    0.06
    对应
    0.06
     justifications
    0.06
    psych
    0.06
     स्ट्रीमिंग
    0.06
     социа
    0.06
     psychologically
    0.06
    Activations Density 0.055%

    No Known Activations