© 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. 120824
    Prev
    Next
    INDEX
    Explanations

    police action and duty

    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
     governmental
    -0.07
    卻
    -0.07
     Governmental
    -0.06
     balsamic
    -0.06
     bilingual
    -0.06
    莫名
    -0.06
     ayat
    -0.06
    ಗೋ
    -0.06
     triglycer
    -0.06
     trono
    -0.06
    POSITIVE LOGITS
    コントロール
    0.06
     control
    0.06
     रोचक
    0.06
     balance
    0.06
    গীর
    0.06
    会話
    0.06
     Wh
    0.06
     prevent
    0.05
    admin
    0.05
     ხელ
    0.05
    Activations Density 0.025%

    No Known Activations