© 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. 39577
    Prev
    Next
    INDEX
    Explanations

    closing punctuation in code

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

    The neuron specializes in detecting numeric literals (number tokens) in code snippets.

    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
    ern
    -0.88
    ぞれ
    -0.85
     habría
    -0.85
     supuestamente
    -0.84
    BINARY
    -0.84
    tid
    -0.84
    hou
    -0.83
    gulation
    -0.81
     desean
    -0.81
    otrop
    -0.78
    POSITIVE LOGITS
    География
    0.97
     båda
    0.93
     cilindros
    0.91
    ᅠ
    0.87
    parade
    0.83
    の位置
    0.83
    ིག་
    0.83
    ٩
    0.83
    vielen
    0.83
     esmalte
    0.82
    Activations Density 0.035%

    No Known Activations