© 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. 56891
    Prev
    Next
    INDEX
    Explanations

    full width or absolute positioning

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

    The neuron selectively fires on numeric literals (e.g. dimensions, pixel values, percentages) in code or markup.

    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
    ⁈
    -0.86
    Contexto
    -0.86
    Mə
    -0.84
    Buongiorno
    -0.84
    しますね
    -0.80
    NSNumber
    -0.79
    Слайд
    -0.79
    садка
    -0.77
    Transcripción
    -0.77
    assertj
    -0.77
    POSITIVE LOGITS
    fullWidth
    2.20
     full
    1.96
     entire
    1.93
    全
    1.67
     весь
    1.58
    Entire
    1.57
    FULL
    1.56
     across
    1.53
     всю
    1.52
    Full
    1.48
    Activations Density 0.041%

    No Known Activations