© 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. 34-GEMMASCOPE-RES-131K
    7. 118294
    Prev
    Next
    INDEX
    Explanations

    thank you, please

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

    The neuron strongly activates on polite request and gratitude phrases (e.g. “please,” “help,” “thanks,” “appreciated”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     therefore
    -1.19
    所以
    -1.17
     then
    -1.15
     so
    -1.14
     HOPE
    -1.05
     hope
    -1.02
     departament
    -1.02
     that
    -1.01
     a
    -0.98
    希望
    -0.96
    POSITIVE LOGITS
    Föld
    1.26
     worst
    1.13
    Worst
    1.13
     ileti
    1.09
     Worst
    1.08
     vielleicht
    1.07
    Until
    1.06
     feel
    1.06
    畢竟
    1.06
    实在是
    1.05
    Activations Density 0.069%

    No Known Activations