© 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. 34-GEMMASCOPE-RES-131K
    4. 59803
    Prev
    Next
    INDEX
    Explanations

    history of

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

    The neuron activates primarily on the word “History,” especially when it appears as a section or article title.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     estrutura
    -0.96
     трени
    -0.93
     asesin
    -0.91
    ynki
    -0.90
     utilizados
    -0.89
    Regel
    -0.88
     Республики
    -0.88
     COMPLETE
    -0.87
     сообщения
    -0.87
     desplaz
    -0.87
    POSITIVE LOGITS
     lesson
    1.58
     of
    1.37
     lessons
    1.34
    lesson
    1.11
     books
    1.11
    book
    1.07
     History
    1.05
     timeline
    1.03
    沿革
    1.02
     history
    1.02
    Activations Density 0.037%

    No Known Activations