© 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. 56747
    Prev
    Next
    INDEX
    Explanations

    don't or negation

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

    The neuron strongly activates on imperative, second-person commands or instructions (e.g. “Hands up,” “Look — but leave no trace,” “Just don’t expect…”).

    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
    not
    -0.96
    Isn
    -0.90
    Haven
    -0.85
     Haven
    -0.81
     vilja
    -0.78
    わけ
    -0.78
     will
    -0.77
     []:
    -0.77
    haven
    -0.76
    may
    -0.75
    POSITIVE LOGITS
     don
    7.41
     dont
    3.89
     jangan
    3.61
     Don
    3.38
     đừng
    3.33
    Dont
    3.28
    Don
    3.23
    不要
    3.20
    don
    3.08
    dont
    3.06
    Activations Density 0.102%

    No Known Activations