© 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. 10-GEMMASCOPE-RES-131K
    7. 102404
    Prev
    Next
    INDEX
    Explanations

    regular in code and math

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

    the word "regular" in technical or code-related contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on occurrences of the standalone word “regular” (in any casing).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     But
    -2.97
    ↵↵
    -2.91
     dismal
    -2.84
     bizarre
    -2.83
     ........
    -2.81
     superb
    -2.78
     spectacular
    -2.77
     splendid
    -2.75
     .......
    -2.75
     magnificent
    -2.72
    POSITIVE LOGITS
    Even
    3.06
    
    2.98
    鷓
    2.94
    沇
    2.84
    get
    2.75
    蛧
    2.69
     weirdly
    2.67
     expertly
    2.61
     undeniably
    2.58
     allow
    2.56
    Activations Density 0.008%

    No Known Activations