© 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. 67438
    Prev
    Next
    INDEX
    Explanations

    access modifiers

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

    The neuron fires on programming‐language visibility keywords (like “public” or “pub”) that introduce declarations.

    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
     it
    -2.08
     many
    -1.72
     helps
    -1.67
     has
    -1.63
     do
    -1.63
     have
    -1.63
     provide
    -1.61
     had
    -1.60
     any
    -1.55
     just
    -1.52
    POSITIVE LOGITS
     trám
    1.92
    küche
    1.52
    
    1.41
     素描
    1.40
    沵
    1.37
     weihnachten
    1.34
    𨭎
    1.34
     唯美
    1.34
     การ์ตูน
    1.34
     ACTUALLY
    1.33
    Activations Density 0.002%

    No Known Activations