© 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. 16689
    Prev
    Next
    INDEX
    Explanations

    programming code libraries

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

    The neuron fires on code‐specific identifiers (file paths, header names, module/class names, import paths, etc.) rather than ordinary English words.

    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
     Tư
    -1.00
     sué
    -0.98
    licante
    -0.98
     reisen
    -0.97
     évé
    -0.94
    сви
    -0.93
     TÉ
    -0.92
    ыр
    -0.92
     Médico
    -0.91
    Köszi
    -0.89
    POSITIVE LOGITS
    那些
    1.08
     items
    0.91
     aquellos
    0.90
     groups
    0.89
     those
    0.88
     definitions
    0.85
     Chinook
    0.84
    .”
    0.83
     लिए
    0.81
    .",
    0.81
    Activations Density 0.004%

    No Known Activations