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. 174
    Prev
    Next
    INDEX
    Explanations

    Confucianism

    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
    agami
    -0.74
    moire
    -0.74
     Stav
    -0.73
    elski
    -0.73
    šak
    -0.73
     Habib
    -0.73
    Sexo
    -0.71
     NHK
    -0.71
    Granada
    -0.70
    エット
    -0.69
    POSITIVE LOGITS
     Confucius
    1.13
     Confucian
    1.01
    Conf
    0.96
    孔
    0.87
     孔
    0.86
    充
    0.86
     rectification
    0.85
     ethical
    0.84
     Ethical
    0.82
     Sage
    0.81
    Activations Density 0.011%

    No Known Activations