© 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. 10-GEMMASCOPE-RES-131K
    7. 113973
    Prev
    Next
    INDEX
    Explanations

    not being

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

    The neuron specializes in detecting the word “not” (i.e. explicit negation).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    家乡
    -1.58
     editar
    -1.57
     �
    -1.54
     моде
    -1.48
     Lös
    -1.45
     abbildung
    -1.45
    -1.45
     profession
    -1.45
     When
    -1.44
     Â
    -1.43
    POSITIVE LOGITS
    which
    1.61
    joke
    1.55
    های
    1.50
    
    1.45
     sii
    1.45
     especiais
    1.42
    vail
    1.41
     wanting
    1.41
    をはじめ
    1.40
    囖
    1.40
    Activations Density 0.029%
    No Known Activations