© 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. 58090
    Prev
    Next
    INDEX
    Explanations

    alternatives presented with 'or'

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

    The neuron fires on the coordinating conjunction “or,” detecting instances of “or” used to present alternatives.

    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
    Ɑ
    -1.46
    点此
    -1.46
     (!__
    -1.45
    там
    -1.40
     únicas
    -1.39
    侂
    -1.39
    苙
    -1.38
    幔
    -1.37
    Posté
    -1.35
    gleichen
    -1.34
    POSITIVE LOGITS
     to
    2.31
     has
    1.98
     should
    1.98
     have
    1.92
     the
    1.92
     our
    1.86
     its
    1.86
     by
    1.85
     see
    1.63
     through
    1.60
    Activations Density 0.034%

    No Known Activations