© 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. 68917
    Prev
    Next
    INDEX
    Explanations

    programming constructs

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

    This neuron fires on variable names in method or constructor parameter lists.

    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
    aucune
    -1.27
    âh
    -1.16
    
    -1.10
    osgi
    -1.09
    itename
    -1.09
    ")[
    -1.09
    wyt
    -1.07
     "@/
    -1.07
    щается
    -1.07
    enteri
    -1.07
    POSITIVE LOGITS
    焢
    1.07
    個人的には
    1.07
    极其
    1.03
    そういえば
    1.03
     тему
    1.03
    這個
    1.00
    哪怕
    1.00
    𝑗
    0.97
    wać
    0.96
     obtenidos
    0.96
    Activations Density 0.001%

    No Known Activations