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. 231
    Prev
    Next
    INDEX
    Explanations

    digital heritage

    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
     McAfee
    -0.79
     vestig
    -0.75
     psycholog
    -0.73
     Udemy
    -0.72
     blad
    -0.72
    ksessa
    -0.71
     fecond
    -0.71
    physiology
    -0.71
     Statisti
    -0.70
    鉅
    -0.69
    POSITIVE LOGITS
     humanities
    3.16
     Humanities
    2.73
     humanistic
    1.52
     humanist
    1.34
     Geistes
    1.32
     scholars
    1.30
     digital
    1.25
     Digital
    1.25
    Digital
    1.23
     scholar
    1.16
    Activations Density 0.055%

    No Known Activations