© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130611
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on programming‐related identifiers (e.g. table/column names, variable or class names in code) rather than ordinary English words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    extracting identifiers and fields

    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
    Not in Any Lists

    No Comments

    Negative Logits
     attorney
    -0.96
     insulin
    -0.94
     е
    -0.85
     Academic
    -0.80
     foo
    -0.79
     Córdoba
    -0.79
     offspring
    -0.78
     intérieur
    -0.77
     java
    -0.77
     interior
    -0.77
    POSITIVE LOGITS
    anolamine
    0.98
    情報は
    0.94
     from
    0.90
    ől
    0.90
     الوطنيه
    0.88
    малар
    0.85
     corresponding
    0.85
    toolStripButton
    0.84
    ById
    0.84
    ASSOC
    0.83
    Activations Density 0.037%

    No Known Activations