© 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. 22-GEMMASCOPE-RES-131K
    7. 98498
    Prev
    Next
    INDEX
    Explanations

    asking how things are doing

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

    The neuron detects informal status‐check questions or statements of “how … doing,” e.g. inquiries about progress or well‐being.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     доказа
    -1.05
     that
    -1.01
     cualquier
    -0.93
     Gelände
    -0.93
     Forscher
    -0.89
     sachsen
    -0.88
     erwar
    -0.86
     ways
    -0.86
     produzione
    -0.85
    Возраст
    -0.85
    POSITIVE LOGITS
     on
    1.35
     compared
    1.23
     fared
    1.10
    を採用
    1.05
    idler
    1.05
    情况
    1.04
     Prospects
    1.02
    整体
    1.01
     respecto
    1.00
    toll
    0.98
    Activations Density 0.036%

    No Known Activations