© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59834
    Prev
    Next
    INDEX
    Explanations

    requesting help or thanks

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

    This neuron detects polite expressions of gratitude or help requests (e.g. “thanks,” “thank you,” “help me”).

    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
     ProtoMessage
    -1.34
     penggunaan
    -1.30
     neuen
    -1.29
     the
    -1.27
     and
    -1.25
    ztes
    -1.23
    的重要
    -1.23
     wichtige
    -1.22
     wichtigen
    -1.22
     menggunakan
    -1.21
    POSITIVE LOGITS
    いよいよ
    1.59
    romeda
    1.45
    今年の
    1.39
    まずは
    1.38
    如果你
    1.34
    新型コロナ
    1.30
    コロナ
    1.29
    這個
    1.29
    娛樂
    1.27
    這是
    1.27
    Activations Density 0.202%

    No Known Activations