© 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. 90021
    Prev
    Next
    INDEX
    Explanations

    questions starting with do you or are you

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

    The neuron strongly activates on direct second-person question prompts (e.g. “Do you…?”, “Are you…?”, “Have you…?”) addressing the reader.

    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
    معرفی
    -1.13
    توضیحات
    -1.05
     seksi
    -1.04
     kanan
    -1.04
    tych
    -0.98
    を設置
    -0.97
     aik
    -0.97
     puisque
    -0.96
    creat
    -0.96
     kaw
    -0.96
    POSITIVE LOGITS
     or
    1.70
     your
    1.69
     wondered
    1.44
    Are
    1.27
    Sometimes
    1.24
     Sometimes
    1.19
     yourself
    1.17
     récente
    1.10
    вор
    1.09
     wondering
    1.09
    Activations Density 0.069%

    No Known Activations