© 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. 11036
    Prev
    Next
    INDEX
    Explanations

    javascript require statements

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

    The neuron activates on numeric tokens (integer or decimal literals) in the 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
    𓐍
    -1.16
     SqlDbType
    -1.14
    玙
    -1.05
     compagnon
    -1.05
     différents
    -1.02
     обновления
    -1.00
     indicó
    -1.00
    uose
    -0.99
     acesso
    -0.98
     sprawd
    -0.98
    POSITIVE LOGITS
    It
    1.05
     it
    1.02
     Эти
    0.97
     It
    0.94
    Alguns
    0.88
    indade
    0.86
     Шаг
    0.86
     Ironically
    0.86
     isabel
    0.85
     AHL
    0.85
    Activations Density 0.013%

    No Known Activations