© 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. 47514
    Prev
    Next
    INDEX
    Explanations

    integration of concepts or components

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

    The neuron responds to occurrences of the word “integrate” (and its morphological variants such as “integrated,” “integration,” etc.).

    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
    '
    -2.61
     längere
    -2.27
    ↵↵
    -1.99
     vernünf
    -1.85
     gän
    -1.77
     большой
    -1.77
     umgangssprach
    -1.75
    ㈰
    -1.74
     names
    -1.72
    サキ
    -1.72
    POSITIVE LOGITS
    摃
    2.31
     integrates
    2.00
    ୌ
    1.96
     integrate
    1.86
    诶
    1.83
    .”
    1.82
    ではでは
    1.82
    llten
    1.80
     Integration
    1.80
    atação
    1.79
    Activations Density 0.040%

    No Known Activations