© 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. 54456
    Prev
    Next
    INDEX
    Explanations

    personal names followed by punctuation

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

    The neuron activates on tokens found in email header metadata—names, dates, times, and related header fields.

    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
     chré
    -1.49
    ֩
    -1.45
     religieuses
    -1.35
     naturen
    -1.35
     keramik
    -1.32
    ׇ
    -1.30
     for
    -1.30
     first
    -1.26
     religieux
    -1.24
     even
    -1.18
    POSITIVE LOGITS
     бампер
    1.52
    ֶּ
    1.47
    ּוֹ
    1.44
     lección
    1.37
    athered
    1.29
    ָּ
    1.23
     actualizada
    1.23
    ־ה
    1.22
     trám
    1.22
     السياس
    1.22
    Activations Density 0.159%

    No Known Activations