© 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. 22-GEMMASCOPE-RES-131K
    7. 12596
    Prev
    Next
    INDEX
    Explanations

    code constructs

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

    This neuron fires on code tokens that are names of singleton or static‐property accessors (e.g. “Instance”, “Current”, “Session”, “UserDefaults”, “Dispatcher”).

    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
     isolada
    -1.25
     Каждый
    -1.21
    centiles
    -1.20
     beschlossen
    -1.19
     gefeiert
    -1.18
     empuj
    -1.16
     Многие
    -1.16
     amenaz
    -1.14
     ergän
    -1.13
     estren
    -1.13
    POSITIVE LOGITS
     (
    1.21
    了你
    1.04
     in
    1.02
     started
    1.02
    hadapi
    1.01
     butterknife
    0.99
    znám
    0.92
    ⮜
    0.92
    lijke
    0.90
     אַ
    0.90
    Activations Density 0.006%

    No Known Activations