© 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. 128165
    Prev
    Next
    INDEX
    Explanations

    gun control, safety, prevention

    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
     agricultura
    -0.06
    自由
    -0.06
     situação
    -0.06
     కొంత
    -0.06
     기업
    -0.06
     memungkinkan
    -0.06
    を経
    -0.06
    Liberal
    -0.06
     Accounting
    -0.06
     navigated
    -0.06
    POSITIVE LOGITS
     safety
    0.09
    safety
    0.08
     безопасность
    0.08
     Safety
    0.08
    Safety
    0.07
     preventative
    0.07
     preventive
    0.07
     prevention
    0.07
     banning
    0.07
     keamanan
    0.06
    Activations Density 0.011%

    No Known Activations