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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8742
    Prev
    Next
    INDEX
    Explanations

    educational statistics and comparisons

    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
     most
    -0.86
     uses
    -0.84
    ítu
    -0.79
     Desember
    -0.78
    изнь
    -0.78
    ニ
    -0.77
    Copa
    -0.77
    вні
    -0.77
    kuat
    -0.77
    Wohn
    -0.76
    POSITIVE LOGITS
     educational
    1.05
    中途
    0.95
     education
    0.91
     vocational
    0.90
     unbelievably
    0.89
     Vocational
    0.88
     attendance
    0.88
     KEEP
    0.87
     adultes
    0.85
    Dropout
    0.84
    Activations Density 0.001%

    No Known Activations