© 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. 119736
    Prev
    Next
    INDEX
    Explanations

    fairness and equitable situations

    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
     під
    -0.06
    厈
    -0.06
     успі
    -0.06
    ว่าเป็น
    -0.06
     nervous
    -0.06
     polskich
    -0.06
    近年来
    -0.06
    езда
    -0.06
     latent
    -0.06
     сни
    -0.06
    POSITIVE LOGITS
     unequal
    0.07
     계산
    0.07
     fair
    0.07
    公平
    0.07
     ন্যায্য
    0.07
     faire
    0.06
     equitable
    0.06
     fairer
    0.06
     справед
    0.06
     Fair
    0.06
    Activations Density 0.030%

    No Known Activations