© 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. 24996
    Prev
    Next
    INDEX
    Explanations

    layout dimensions and code separators

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

    The neuron is triggered by numeric literals (numbers) in code or markup.

    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
    Pratique
    -0.97
     images
    -0.97
    ‌.
    -0.96
     it
    -0.94
     data
    -0.93
    Exemples
    -0.91
     algunos
    -0.90
     this
    -0.90
    वरण
    -0.90
     Kartoff
    -0.89
    POSITIVE LOGITS
     kleinere
    0.92
     steeped
    0.91
     downright
    0.89
     autres
    0.89
    eraard
    0.87
     anderen
    0.86
     Ra
    0.85
     التالية
    0.85
    limiento
    0.85
     anderer
    0.84
    Activations Density 0.000%

    No Known Activations