© 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. 68498
    Prev
    Next
    INDEX
    Explanations

    created on or they look

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

    This neuron detects Jupyter/IPython notebook input‐prompt markers (the “In [ … ]:” tokens).

    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
     if
    -2.20
    {
    -2.06
    C
    -1.93
    <b>
    -1.88
    '
    -1.82
     you
    -1.79
    If
    -1.73
     when
    -1.70
     as
    -1.66
    after
    -1.65
    POSITIVE LOGITS
     asemenea
    1.86
    咘
    1.84
    刄
    1.75
    垰
    1.73
    嗵
    1.70
    ⁛
    1.65
    ܜ
    1.64
    齶
    1.63
     ませ
    1.63
    vať
    1.62
    Activations Density 0.001%

    No Known Activations