© 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. 36005
    Prev
    Next
    INDEX
    Explanations

    questions starting with do

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

    The neuron specifically detects occurrences of the auxiliary verb “do” (and its variant “does”), as used in forming 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_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
     in
    -1.53
     is
    -1.47
    參考資料
    -1.38
    <bos>
    -1.38
     at
    -1.37
    穫
    -1.34
     before
    -1.34
    結局
    -1.30
     including
    -1.28
    1
    -1.28
    POSITIVE LOGITS
     you
    3.00
     they
    2.30
     olacaktır
    2.03
    えっ
    2.03
     yayınları
    1.95
    ほら
    1.95
     we
    1.91
    つづく
    1.88
     môžete
    1.77
    katalog
    1.75
    Activations Density 0.038%

    No Known Activations