© 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. 56944
    Prev
    Next
    INDEX
    Explanations

    "no" followed by a noun

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

    This neuron fires on standalone occurrences of the word “no” (especially at the start of phrases or sentences).

    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
     confirme
    -1.36
     alarme
    -1.30
     réfugi
    -1.27
    któ
    -1.25
     sumar
    -1.23
     activiteiten
    -1.22
    ſſen
    -1.21
     condam
    -1.20
     interessantes
    -1.20
     intensif
    -1.19
    POSITIVE LOGITS
     way
    2.30
     such
    1.91
     need
    1.80
     reason
    1.74
     "
    1.62
     point
    1.62
     question
    1.53
     avoiding
    1.52
     information
    1.52
     going
    1.48
    Activations Density 0.025%

    No Known Activations