© 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. 64525
    Prev
    Next
    INDEX
    Explanations

    code comments and documentation

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

    The neuron selectively activates on standalone numeric tokens (e.g. those large numbers embedded in comments or docstrings).

    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
    嫆
    -2.22
    Beskrivning
    -1.86
    Leírás
    -1.84
    тися
    -1.80
     köy
    -1.75
    ឵
    -1.73
     namun
    -1.71
     Spanien
    -1.70
    は
    -1.67
    ądze
    -1.66
    POSITIVE LOGITS
    {
    2.28
    P
    2.22
    Y
    2.08
    >
    2.03
     a
    1.84
    ’
    1.77
    _
    1.75
    U
    1.72
    -
    1.71
     was
    1.70
    Activations Density 0.001%

    No Known Activations