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. 8442
    Prev
    Next
    INDEX
    Explanations

    some measure or degree

    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
    lography
    -0.79
     AllMusic
    -0.77
    Merci
    -0.75
    屾
    -0.74
     Jerzy
    -0.74
     实例
    -0.74
    ÍAS
    -0.73
     Dijo
    -0.73
    ución
    -0.73
     membre
    -0.73
    POSITIVE LOGITS
     degree
    1.54
     level
    1.34
     extent
    1.34
     form
    1.28
     fashion
    1.09
     Degree
    1.09
     point
    1.09
     capacity
    0.98
     shape
    0.98
    way
    0.97
    Activations Density 0.022%

    No Known Activations