Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8448
    Prev
    Next
    INDEX
    Explanations

    bias AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crust
    -0.72
    フォト
    -0.71
    Проце
    -0.71
    gaver
    -0.71
     яйца
    -0.71
     aco
    -0.70
     露
    -0.70
    Сту
    -0.68
    indicator
    -0.67
     volonté
    -0.67
    POSITIVE LOGITS
    Bias
    0.89
     genealogy
    0.82
    bias
    0.81
    allel
    0.80
     duiz
    0.79
    NIST
    0.78
     Rek
    0.77
     biased
    0.77
     AI
    0.76
     facial
    0.75
    Activations Density 0.021%

    No Known Activations