© 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. 34-GEMMASCOPE-RES-131K
    7. 89804
    Prev
    Next
    INDEX
    Explanations

    Ruby symbols or keywords

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

    The neuron is looking for code‐specific punctuation and keywords (especially colons, parentheses, module/function names, and annotations) characteristic of Elixir (or similar) source 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_34/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
     которые
    -0.75
     fortfarande
    -0.73
    鏢
    -0.72
    
    -0.71
     Saginaw
    -0.71
    είτε
    -0.70
    飲食
    -0.68
     Hopefully
    -0.68
    isNot
    -0.67
    每个
    -0.66
    POSITIVE LOGITS
     [:
    1.75
    [:
    1.75
     symbol
    1.40
     Symbol
    1.39
    Symbol
    1.32
     :
    1.32
     symbols
    1.30
    ][:
    1.22
    =:
    1.20
    symbol
    1.16
    Activations Density 0.043%

    No Known Activations