© 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. 116039
    Prev
    Next
    INDEX
    Explanations

    voltage control

    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
     attained
    -0.06
     satisfies
    -0.06
     attainment
    -0.06
     ఉన్న
    -0.06
     Everyday
    -0.06
     attains
    -0.06
     thrift
    -0.06
     万元
    -0.06
     выполнение
    -0.06
     Comfortable
    -0.06
    POSITIVE LOGITS
     수정
    0.07
     beso
    0.06
    修正
    0.06
    适用于
    0.06
     നൽക
    0.06
    適用
    0.06
     Suu
    0.06
    修复
    0.06
    后的
    0.06
    柱
    0.06
    Activations Density 0.002%

    No Known Activations