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. 14
    Prev
    Next
    INDEX
    Explanations

    bubble

    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
    ài
    -0.79
     unfolding
    -0.78
    出身
    -0.77
    Ucraina
    -0.74
     おり
    -0.71
    تے
    -0.71
    ída
    -0.70
    nesses
    -0.69
    とする
    -0.69
    のようです
    -0.69
    POSITIVE LOGITS
    gum
    1.68
     bubble
    1.58
     Bubble
    1.55
    bubble
    1.52
    bubbles
    1.39
     bubbles
    1.36
     bub
    1.34
    Bubble
    1.26
    Bubbles
    1.23
     Bubbles
    1.20
    Activations Density 0.017%

    No Known Activations