© 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. 19481
    Prev
    Next
    INDEX
    Explanations

    begin and end

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

    The neuron fires on the C++ iterator method names “begin” and “end.”

    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
     “
    -1.56
    y
    -1.45
    ！」
    -1.38
    CELLANEOUS
    -1.36
    se
    -1.35
     poignant
    -1.35
     Â
    -1.34
    %",
    -1.34
     a
    -1.33
     En
    -1.31
    POSITIVE LOGITS
    اين
    1.56
     Redewendung
    1.53
     verwijzen
    1.52
    essai
    1.49
    躱
    1.42
     Imágenes
    1.41
    However
    1.41
    スムーズ
    1.40
     Colección
    1.40
     イヤー
    1.38
    Activations Density 0.001%

    No Known Activations