© 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. 114149
    Prev
    Next
    INDEX
    Explanations

    adverbs followed by prepositions

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

    The neuron fires on adverbial modifiers (especially words ending in “-ly”).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     moldura
    -1.84
     when
    -1.64
    趼
    -1.63
    ଢ
    -1.60
    蒾
    -1.57
    渼
    -1.55
     naše
    -1.55
     maleta
    -1.52
     almofada
    -1.52
     nové
    -1.48
    POSITIVE LOGITS
     to
    2.31
     into
    1.89
    ↵↵
    1.81
     on
    1.57
     in
    1.55
    D
    1.55
     ciś
    1.50
    UPAC
    1.49
     разница
    1.48
    ↵
    1.44
    Activations Density 0.086%

    No Known Activations