© 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. 116069
    Prev
    Next
    INDEX
    Explanations

    principles and authorities

    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
     reassurance
    -0.06
     jedem
    -0.06
     เป็น
    -0.06
     jeder
    -0.06
     guise
    -0.06
    must
    -0.06
    每
    -0.06
    য়াত
    -0.06
     حالة
    -0.06
     Apesar
    -0.06
    POSITIVE LOGITS
     principles
    0.09
     Principles
    0.07
     objectivity
    0.07
    這些
    0.06
     these
    0.06
    ovane
    0.06
    这些
    0.06
     the
    0.06
    principles
    0.06
     abilities
    0.06
    Activations Density 0.008%

    No Known Activations