© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82802
    Prev
    Next
    INDEX
    Explanations

    thread and context

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

    This neuron detects code identifiers written in snake_case (especially long configuration or session/context variable names).

    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
    ミア
    -0.73
    交给
    -0.70
     maquilla
    -0.69
     LOSS
    -0.68
     kontrol
    -0.68
     vedo
    -0.67
    Hua
    -0.67
    definitions
    -0.67
    ATRE
    -0.66
     pét
    -0.66
    POSITIVE LOGITS
     Thread
    1.95
    Thread
    1.81
    thread
    1.73
     thread
    1.71
     threads
    1.44
    THREAD
    1.38
    线程
    1.27
     THREAD
    1.26
     TLS
    1.23
    ContextHolder
    1.21
    Activations Density 0.040%

    No Known Activations