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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71193
    Prev
    Next
    INDEX
    Explanations

    programming keywords and code elements

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

    This neuron fires on technical or code-specific terms—especially programming keywords, SQL/Go identifiers, and uppercase acronyms.

    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
     …
    -0.91
     más
    -0.85
    ↵↵↵↵↵
    -0.83
     Outils
    -0.82
     ...
    -0.82
    ホ
    -0.82
    智慧
    -0.82
    ）
    -0.81
     ك
    -0.80
    -\\
    -0.79
    POSITIVE LOGITS
     dáms
    0.99
    ⾥
    0.99
    Влади
    0.97
    again
    0.97
     dámské
    0.96
    Again
    0.96
     satisfactor
    0.94
    Вариан
    0.93
    どこに
    0.93
    INGRED
    0.93
    Activations Density 0.058%

    No Known Activations