© 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. 10-GEMMASCOPE-RES-131K
    7. 69551
    Prev
    Next
    INDEX
    Explanations

    configuration files

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

    The neuron fires on mentions of configuration files or config-related parameters (e.g. “config file,” “configuration,” “ConfigFile,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ྵ
    -1.89
    面色
    -1.84
    knows
    -1.80
     rescat
    -1.78
     イエロー
    -1.77
    ㇼ
    -1.77
    骉
    -1.77
    跸
    -1.75
    becomes
    -1.73
    
    -1.73
    POSITIVE LOGITS
    in
    1.77
    With
    1.70
     has
    1.66
    Still
    1.65
    Since
    1.62
     这个
    1.60
    ついで
    1.59
    裡
    1.57
     條
    1.57
    區域
    1.55
    Activations Density 0.013%

    No Known Activations