© 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. 65386
    Prev
    Next
    INDEX
    Explanations

    code structures and keywords

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

    The neuron is triggered by code lines performing variable or property assignments (i.e. “=” assignments) across different programming languages.

    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
     in
    -2.47
     or
    -2.06
     During
    -2.02
     but
    -1.95
     all
    -1.83
     There
    -1.75
     После
    -1.73
     или
    -1.73
    natured
    -1.71
     While
    -1.64
    POSITIVE LOGITS
    ↵
    1.89
     нашего
    1.82
     naszego
    1.81
     récemment
    1.80
     magnific
    1.77
    桫
    1.73
     thre
    1.73
    
    1.72
     consequ
    1.70
     utilisé
    1.70
    Activations Density 0.153%

    No Known Activations