© 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. 68693
    Prev
    Next
    INDEX
    Explanations

    comparing two lists or variables

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

    The neuron primarily activates on numeric literals (numbers) 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_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
     vinagre
    -0.93
    etur
    -0.91
    glises
    -0.90
     teclas
    -0.88
    izedBox
    -0.88
     vět
    -0.87
    Auszeichnungen
    -0.87
    릎
    -0.87
     jinak
    -0.87
     henceforth
    -0.85
    POSITIVE LOGITS
    Comparing
    1.10
     counterpart
    0.99
    We
    0.97
    If
    0.95
    It
    0.94
     comparing
    0.94
    ive
    0.93
    comparing
    0.89
     comparison
    0.88
    That
    0.87
    Activations Density 0.018%

    No Known Activations