© 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. 104499
    Prev
    Next
    INDEX
    Explanations

    number 2 in code contexts

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

    the digit "2" appearing in variable names, function names, or code identifiers.

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

    The neuron strongly activates on standalone numeric literals (especially the digit “2”) in code.

    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
     touted
    -2.42
     ostensibly
    -2.20
     superbly
    -2.00
     epitom
    -1.98
     embodies
    -1.95
     oddly
    -1.91
     artful
    -1.91
     enhances
    -1.84
     cleverly
    -1.84
     haphazard
    -1.83
    POSITIVE LOGITS
     dando
    2.13
     ใน
    2.08
    '
    1.98
    
    1.92
    睹
    1.89
    usschuss
    1.87
     😊
    1.86
     lmao
    1.84
     :/
    1.84
     astonishing
    1.82
    Activations Density 0.039%

    No Known Activations