© 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. 30021
    Prev
    Next
    INDEX
    Explanations

    deliver or send goods

    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
     föld
    -1.09
    なのかな
    -0.93
     Vorstand
    -0.92
    騙
    -0.91
    だな
    -0.88
    Simpson
    -0.84
     csomag
    -0.83
    リーの
    -0.83
    getPassword
    -0.81
     lentejuelas
    -0.81
    POSITIVE LOGITS
    deliver
    1.05
     DELIVER
    1.03
     deliver
    0.94
     għall
    0.93
    Deliver
    0.90
     delivered
    0.89
     Deliver
    0.83
     garant
    0.81
    いため
    0.81
     точку
    0.79
    Activations Density 0.001%

    No Known Activations