© 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. 62512
    Prev
    Next
    INDEX
    Explanations

    passive verb phrases

    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
    capped
    -1.10
    着了
    -1.07
    makeatother
    -1.01
    ico
    -0.99
    始めた
    -0.98
    populated
    -0.98
    lified
    -0.98
    tiéndose
    -0.95
    BorderFactory
    -0.94
    ach
    -0.93
    POSITIVE LOGITS
     sent
    1.38
     delivered
    1.35
     purchased
    1.35
     sold
    1.27
     eaten
    1.15
     shipped
    1.14
     placed
    1.13
     in
    1.11
     auction
    1.06
     returned
    1.05
    Activations Density 0.118%

    No Known Activations