© 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. 34-GEMMASCOPE-RES-131K
    7. 57059
    Prev
    Next
    INDEX
    Explanations

    closing tags and code delimiters

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

    This neuron detects numeric tokens (strings of digits) in code or markup.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -2.20
     as
    -1.91
     so
    -1.75
     over
    -1.74
     just
    -1.73
     at
    -1.70
     make
    -1.70
     three
    -1.70
     with
    -1.66
     two
    -1.66
    POSITIVE LOGITS
    ↵
    2.02
     juſ
    1.81
     quintessential
    1.80
    :</
    1.73
    ?</
    1.72
     bascul
    1.71
     malé
    1.70
    豋
    1.66
     délais
    1.64
    /</
    1.63
    Activations Density 0.035%

    No Known Activations