© 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. 22-GEMMASCOPE-RES-131K
    7. 64360
    Prev
    Next
    INDEX
    Explanations

    relative clauses that introduce verbs

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     or
    -1.45
     such
    -1.17
     then
    -1.13
     in
    -1.13
    ₋
    -1.11
    וּ
    -1.10
    𝟐
    -1.10
     грн
    -1.09
     heilig
    -1.04
     since
    -1.03
    POSITIVE LOGITS
    却
    1.17
     everyone
    1.16
     everything
    1.14
     nothing
    1.14
     nobody
    1.13
     endereço
    1.13
    却又
    1.12
    椁
    1.11
     everybody
    1.09
     totalité
    1.09
    Activations Density 0.037%

    No Known Activations