© 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. 10-GEMMASCOPE-RES-131K
    7. 45681
    Prev
    Next
    INDEX
    Explanations

    infinitive 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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     at
    -1.91
     because
    -1.85
     or
    -1.80
     the
    -1.70
     have
    -1.67
     atacado
    -1.64
    他会
    -1.61
    诶
    -1.57
     any
    -1.53
     during
    -1.53
    POSITIVE LOGITS
    <b>
    1.88
    ,”
    1.77
    $,
    1.73
    m
    1.71
    np
    1.69
    ш
    1.65
    
    1.64
    rb
    1.63
    mit
    1.57
    ”
    1.55
    Activations Density 0.133%

    No Known Activations