© 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. 22-GEMMASCOPE-RES-131K
    4. 39431
    Prev
    Next
    INDEX
    Explanations

    code context objects

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

    The neuron strongly fires on code identifiers for execution‐ or dispatch‐related context objects (e.g. variables or types named “…Context,” Dispatcher, Chain, OnActionExecuting, 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_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
    isez
    -1.09
    InvalidProtocol
    -0.90
     кръ
    -0.90
     from
    -0.88
     and
    -0.87
     darbu
    -0.85
    adá
    -0.84
    鸷
    -0.83
     Böh
    -0.82
     we
    -0.82
    POSITIVE LOGITS
     wolle
    0.96
     County
    0.90
    donde
    0.87
     RURAL
    0.85
     スイッチ
    0.84
     forested
    0.84
     mercies
    0.84
     createContext
    0.82
    景区
    0.82
     découvrez
    0.81
    Activations Density 0.010%

    No Known Activations