© 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. 98602
    Prev
    Next
    INDEX
    Explanations

    expressions of apology

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

    The neuron detects apology phrases (instances of “sorry” and its immediate follow-on apology wording).

    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
     each
    -1.38
    Vendo
    -1.32
     both
    -1.27
    bảng
    -1.27
     how
    -1.27
    Mvh
    -1.26
    yyv
    -1.23
    管理器
    -1.21
     helps
    -1.20
     suggests
    -1.18
    POSITIVE LOGITS
    \"
    1.24
    É
    1.24
     مترجم
    1.22
     自己
    1.20
    if
    1.20
    ↵
    1.18
    n
    1.16
    &
    1.13
    ,
    1.13
    im
    1.11
    Activations Density 0.013%

    No Known Activations