© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128348
    Prev
    Next
    INDEX
    Explanations

    moral and ethical concepts

    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
     successively
    -0.07
     δεύτε
    -0.07
     speedily
    -0.07
     njegov
    -0.07
    的数据
    -0.06
     mistakenly
    -0.06
    łka
    -0.06
     jego
    -0.06
    它的
    -0.06
     its
    -0.06
    POSITIVE LOGITS
     disability
    0.06
     debate
    0.06
     ethical
    0.06
     ☆
    0.06
    限制
    0.06
     ribbons
    0.06
    公平
    0.06
    চ্ছ
    0.06
       
    0.06
    author
    0.06
    Activations Density 0.010%

    No Known Activations