© 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. 72836
    Prev
    Next
    INDEX
    Explanations

    sources of information

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

    The neuron detects occurrences of the word “Sources,” marking the start of reference or bibliography lists.

    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
     In
    -2.98
    There
    -2.83
    with
    -2.83
    With
    -2.63
     With
    -2.61
     Because
    -2.59
     You
    -2.48
     WITH
    -2.38
    Some
    -2.38
     Like
    -2.34
    POSITIVE LOGITS
    ࿊
    3.08
    Ꝑ
    2.70
    ↑↑↑</
    2.66
    躂
    2.55
    衚
    2.47
    菝
    2.47
    
    2.45
     แต่
    2.44
    sources
    2.42
    ⸫
    2.38
    Activations Density 0.009%

    No Known Activations