© 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. 128957
    Prev
    Next
    INDEX
    Explanations

    Attorney General

    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
     মাঝ
    -0.06
    ･･
    -0.06
     later
    -0.06
    
    -0.06
    ‌ల
    -0.06
    nCount
    -0.06
     exclusively
    -0.06
     LOWER
    -0.06
     یعنی
    -0.06
     denoted
    -0.06
    POSITIVE LOGITS
    不
    0.06
     Listen
    0.06
    上げて
    0.06
    她的
    0.05
     తన
    0.05
     भाग
    0.05
    ;',
    0.05
    जव
    0.05
     आणखी
    0.05
     her
    0.05
    Activations Density 0.003%

    No Known Activations