© 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. 83803
    Prev
    Next
    INDEX
    Explanations

    apostrophe followed by letters

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

    The neuron responds to single‐quote/apostrophe characters (i.e. tokens that are just "'" in text).

    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
    .
    -1.93
     vorliegenden
    -1.92
    ↵↵
    -1.80
     erwor
    -1.77
     erweiterten
    -1.69
     vorhandenen
    -1.68
     veränder
    -1.63
     echten
    -1.59
     obecnie
    -1.59
     internationalen
    -1.58
    POSITIVE LOGITS
    跸
    1.66
     to
    1.44
    跺
    1.43
    %，
    1.42
    )("
    1.38
    rildi
    1.38
    鯷
    1.34
    ⇣
    1.32
    撄
    1.31
    ''.
    1.30
    Activations Density 0.017%

    No Known Activations