© 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. 104274
    Prev
    Next
    INDEX
    Explanations

    please, followed by a request

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

    The neuron fires on polite soliciting/request language—words like “please,” “help,” “me,” “kindly,” “thanks,” etc., that signal the user is asking for something.

    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
     andet
    -1.48
    нисти
    -1.41
     még
    -1.38
    ⃙
    -1.37
     které
    -1.33
    ность
    -1.32
    ın
    -1.29
    踵
    -1.29
     gibi
    -1.28
    MultipartFile
    -1.28
    POSITIVE LOGITS
     demonio
    1.67
     maría
    1.65
    1
    1.55
    although
    1.49
    this
    1.49
    也很
    1.48
    6
    1.48
    4
    1.47
    也沒有
    1.45
     differs
    1.43
    Activations Density 0.036%

    No Known Activations