© 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. 115907
    Prev
    Next
    INDEX
    Explanations

    author list marker

    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
     transitioning
    -0.06
     புது
    -0.06
     astray
    -0.06
     dico
    -0.06
     እንዲሁም
    -0.06
     recommending
    -0.06
     আসবেন
    -0.06
     फर्स्ट
    -0.06
     když
    -0.06
    udur
    -0.06
    POSITIVE LOGITS
     два
    0.06
    两
    0.06
    了两
    0.06
     დღ
    0.06
     этих
    0.06
    两个
    0.06
    하고
    0.06
     шесть
    0.06
     навча
    0.06
     two
    0.06
    Activations Density 0.001%

    No Known Activations