© 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. 56664
    Prev
    Next
    INDEX
    Explanations

    auxiliary and modal 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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    isons
    -0.78
    testens
    -0.74
     mensagem
    -0.70
    Wagon
    -0.69
     unread
    -0.68
    copically
    -0.68
    emia
    -0.68
    dification
    -0.68
     FEST
    -0.67
    mappedBy
    -0.67
    POSITIVE LOGITS
     verb
    4.91
     verbs
    4.75
    verb
    3.63
    Verb
    3.33
    verbs
    3.33
     Verb
    3.22
     Verbs
    3.11
    VERB
    2.84
     verbo
    2.34
     VERB
    2.28
    Activations Density 0.068%

    No Known Activations