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. 207
    Prev
    Next
    INDEX
    Explanations

    babies and birth contexts

    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
    students
    -0.93
     Students
    -0.91
     نوجوان
    -0.90
     ungdom
    -0.88
    ждений
    -0.87
     students
    -0.87
    mente
    -0.85
     Femmes
    -0.82
     MacBook
    -0.82
    Students
    -0.82
    POSITIVE LOGITS
     baby
    2.95
     infant
    2.94
     babies
    2.42
     infants
    2.39
     newborn
    2.31
     Infant
    2.20
    baby
    2.16
     Baby
    2.14
     infancy
    2.11
     Babies
    2.08
    Activations Density 0.065%

    No Known Activations