© 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. 120763
    Prev
    Next
    INDEX
    Explanations

    ethics reform, affordable housing, health issues

    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
    Not in Any Lists

    No Comments

    Negative Logits
    あるいは
    -0.06
     ਜਾਂ
    -0.06
     hadi
    -0.06
     localised
    -0.06
     drugih
    -0.05
    ويات
    -0.05
     різних
    -0.05
     désormais
    -0.05
     hoặc
    -0.05
     outpouring
    -0.05
    POSITIVE LOGITS
     никто
    0.07
     没有
    0.07
     nicht
    0.06
    空気
    0.06
    লেম
    0.06
    auern
    0.06
     내가
    0.06
    ğin
    0.06
     budget
    0.06
     categories
    0.06
    Activations Density 0.011%

    No Known Activations