© 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. 16573
    Prev
    Next
    INDEX
    Explanations

    before or after

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

    The neuron fires on common positional and relational function words—prepositions and adverbs like “before,” “after,” “into,” “next,” “beside,” and “to”—that mark where or when something occurs.

    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
     Chúng
    -0.84
     שלנו
    -0.84
     queryString
    -0.83
    Chúng
    -0.82
    很多
    -0.81
     benef
    -0.81
     вони
    -0.81
    附近
    -0.81
     kentang
    -0.81
    我們
    -0.80
    POSITIVE LOGITS
     each
    1.93
     the
    1.41
    each
    1.30
     mỗi
    1.18
     каждой
    1.10
     names
    1.08
     каждого
    1.07
     your
    1.04
     każdego
    1.02
     написано
    1.02
    Activations Density 0.047%

    No Known Activations