© 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. 32715
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in -ally

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects adverbial or adjectival words formed with the “-ally”/“-ically” suffix.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
     of
    -2.67
    Beberapa
    -1.73
     in
    -1.70
     to
    -1.54
     teknologi
    -1.48
    Lebih
    -1.42
    Karakteristik
    -1.40
    ༛
    -1.39
    Meskipun
    -1.39
    海苔
    -1.36
    POSITIVE LOGITS
     equivalent
    1.64
    
    1.58
     紋
    1.58
     preparado
    1.55
     only
    1.48
     instig
    1.47
     betrachtet
    1.38
    ally
    1.34
    
    1.33
     bolsillos
    1.31
    Activations Density 0.056%

    No Known Activations