© 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. 19818
    Prev
    Next
    INDEX
    Explanations

    asking questions

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

    This neuron strongly activates on interrogative question phrases, signaling it detects questions.

    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
    probably
    -1.83
    >?
    -1.51
     probablement
    -1.50
     evtl
    -1.45
     یکی
    -1.43
    might
    -1.41
     весьма
    -1.41
    should
    -1.41
     bricolaje
    -1.39
    
    -1.39
    POSITIVE LOGITS
    ?
    2.97
     this
    2.72
     además
    1.77
     with
    1.63
     these
    1.59
    屐
    1.55
    れの
    1.50
     in
    1.47
     sitten
    1.44
    ませんか
    1.41
    Activations Density 1.932%

    No Known Activations