© 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. 128023
    Prev
    Next
    INDEX
    Explanations

    each of

    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
     through
    -0.08
     através
    -0.07
     через
    -0.07
     via
    -0.07
     통해
    -0.06
     attraverso
    -0.06
    通過
    -0.06
    dures
    -0.06
     rağmen
    -0.06
     kroz
    -0.06
    POSITIVE LOGITS
    每一个
    0.08
    每一
    0.08
     fiecare
    0.07
    แต่ละ
    0.07
     setiap
    0.07
     каждую
    0.07
     모든
    0.07
    ടുന്ന
    0.07
     each
    0.07
     எல்லா
    0.07
    Activations Density 0.006%

    No Known Activations