© 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. 104685
    Prev
    Next
    INDEX
    Explanations

    shell commands or code snippets

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

    The neuron activates on code fragments defining or using JavaScript/TypeScript functions (e.g. the “function” keyword, parameter names, braces, and “return” statements).

    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
    خخ
    -1.30
     チラシ
    -1.13
     ENERG
    -1.09
    儔
    -1.07
     gerai
    -1.07
     pangan
    -1.03
     brugt
    -1.03
     ヌード
    -1.03
    Donativos
    -1.00
     gekomen
    -1.00
    POSITIVE LOGITS
     if
    1.62
    if
    1.15
    even
    1.08
     $
    1.06
     ihre
    1.05
     bahkan
    1.00
     incluso
    1.00
     decide
    0.98
     THEIR
    0.98
    
    0.96
    Activations Density 0.006%

    No Known Activations