© 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. 128129
    Prev
    Next
    INDEX
    Explanations

    Philippines, elections, service, introduction

    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
     уси
    -0.07
     emphasize
    -0.06
     jeho
    -0.06
    こんな
    -0.06
     πιο
    -0.06
     بلد
    -0.06
    म्ह
    -0.06
    .-
    -0.06
     craze
    -0.06
     hitherto
    -0.06
    POSITIVE LOGITS
     elb
    0.06
    ாய்ச்சி
    0.06
    调用
    0.06
    ued
    0.06
     потім
    0.06
    获取
    0.06
     Iowa
    0.06
    abbati
    0.06
     allen
    0.06
    ম্যান
    0.06
    Activations Density 0.024%

    No Known Activations