© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92352
    Prev
    Next
    INDEX
    Explanations

    distraction and diversion

    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
    蔵
    -0.75
    $}}
    -0.75
    Démographie
    -0.74
    Lamin
    -0.72
    лади
    -0.71
     fortifications
    -0.71
    _]
    -0.71
    Dw
    -0.71
    悔
    -0.69
    Ona
    -0.69
    POSITIVE LOGITS
     distraction
    5.75
     distract
    5.59
     distractions
    5.03
     distracting
    5.03
     distracted
    5.00
     distra
    4.97
     Distra
    4.16
     diversion
    3.86
     divert
    3.56
     diverted
    3.22
    Activations Density 0.091%

    No Known Activations