© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 127791
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric literals (i.e. standalone numbers) in the code.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    jQuery `$(this)` selector

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     to
    -1.59
    適量
    -1.58
    などを
    -1.45
     if
    -1.45
    そして
    -1.32
    などの
    -1.30
     then
    -1.30
    !(
    -1.24
    ~!
    -1.22
     others
    -1.21
    POSITIVE LOGITS
     tuvimos
    1.34
     alltså
    1.30
    urrent
    1.30
     estábamos
    1.30
     körül
    1.26
     alrededores
    1.21
    向けの
    1.21
     betyr
    1.20
     fuimos
    1.18
    際の
    1.18
    Activations Density 0.005%

    No Known Activations