© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3470
    Prev
    Next
    INDEX
    Explanations

    asking or posing questions

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

    The neuron specifically detects occurrences of the verbs “ask” or “asks,” i.e. when a question is being posed.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     situation
    -0.90
    StatusBadRequest
    -0.85
    的内容
    -0.82
     info
    -0.80
    了一种
    -0.80
     requirement
    -0.78
     يف
    -0.78
     extremamente
    -0.78
    这件事情
    -0.77
    ATUR
    -0.77
    POSITIVE LOGITS
     questions
    1.66
     fundamental
    1.59
    fundamental
    1.47
     important
    1.39
     big
    1.36
    important
    1.26
    questions
    1.23
    Fundamental
    1.20
     bigger
    1.14
     importanti
    1.13
    Activations Density 0.179%

    No Known Activations