© 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. 39346
    Prev
    Next
    INDEX
    Explanations

    programming getters and setters

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

    The neuron flags the keyword “get” when it appears as an accessor (i.e. a getter method or property get) in code.

    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
    先週
    -1.02
    ſſen
    -0.99
    camiseta
    -0.98
     jouet
    -0.98
     usadas
    -0.97
    ziem
    -0.97
    asikan
    -0.95
    無し
    -0.95
     okno
    -0.94
     тоже
    -0.94
    POSITIVE LOGITS
    is
    1.03
    ubo
    1.00
     británico
    0.98
     следующее
    0.98
    av
    0.96
    u
    0.95
    kal
    0.94
    绞
    0.94
    1
    0.93
    ковая
    0.92
    Activations Density 0.001%

    No Known Activations