© 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. 250
    Prev
    Next
    INDEX
    Explanations

    leaders, dictators, presidents

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

    This neuron specializes in detecting named-entity tokens—proper names, titles, dates, and other capitalized or numeric identifiers.

    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
     Ministero
    -1.60
     rosso
    -1.48
    特に
    -1.45
     depositphotos
    -1.41
     发表于
    -1.39
     настройки
    -1.38
     リボン
    -1.34
     Inſ
    -1.34
     Buah
    -1.31
     erweitert
    -1.30
    POSITIVE LOGITS
     himself
    2.09
     after
    1.60
    himself
    1.57
     almendras
    1.38
     without
    1.34
     opponent
    1.34
    民众
    1.29
    chedule
    1.26
     during
    1.25
     opponents
    1.23
    Activations Density 0.084%

    No Known Activations