© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56825
    Prev
    Next
    INDEX
    Explanations

    Event.bubbles

    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
    Negative Logits
    ਆਂ
    -0.82
     Sig
    -0.75
    耗
    -0.72
     зави
    -0.69
    啓
    -0.69
    imports
    -0.68
    了
    -0.68
     plates
    -0.68
    シ
    -0.68
    print
    -0.67
    POSITIVE LOGITS
     bubble
    2.11
     bubbles
    2.06
    bubble
    1.91
    Bubble
    1.91
     Bubble
    1.82
     bubbling
    1.80
     BUB
    1.72
    bubbles
    1.70
     Bubbles
    1.67
    Bubbles
    1.58
    Activations Density 0.047%

    No Known Activations