© 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. 21820
    Prev
    Next
    INDEX
    Explanations

    Surrey, empathy, elliptical

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

    The neuron fires on the single standout “topic” or key term in each document (e.g. empathy in psychology papers, Surrey in place‐name entries, Helvetica in font settings)—in other words, it detects the main subject word of a text segment.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mentions of empathy or empathic understanding and related traits

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "empathy" or references to Surrey (a location in England).

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    the
    -4.03
     火鍋
    -2.98
    瞜
    -2.84
    進入
    -2.73
    Beyond
    -2.72
    7
    -2.67
    5
    -2.59
    4
    -2.58
    ing
    -2.55
     keren
    -2.55
    POSITIVE LOGITS
     również
    2.77
     ก็
    2.47
     treacherous
    2.44
    也会
    2.39
     descub
    2.31
    enablog
    2.30
     fortitude
    2.28
    蚌
    2.28
    ࿙
    2.25
    replyreport
    2.23
    Activations Density 0.002%

    No Known Activations