© 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. 56831
    Prev
    Next
    INDEX
    Explanations

    doing and its continuations

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

    The neuron strongly activates on various forms of the verb “do” (e.g. do, doing, did) in the text.

    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
    可以直接
    -0.87
     realização
    -0.83
    Текст
    -0.81
    zzazione
    -0.80
    oyer
    -0.79
    完毕
    -0.79
    一惊
    -0.79
     pemikiran
    -0.78
     简
    -0.78
     possibilities
    -0.78
    POSITIVE LOGITS
     research
    1.16
     charity
    1.14
     some
    1.09
     drugs
    1.06
     lots
    1.05
     circuitos
    1.02
     savait
    1.01
     interviews
    0.98
     laundry
    0.95
     Ленин
    0.92
    Activations Density 0.026%

    No Known Activations