© 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. 6958
    Prev
    Next
    INDEX
    Explanations

    gap between things

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

    The neuron detects mentions of numerical “gaps” or disparities (i.e. references to a gap or quantitative difference between groups).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    âncias
    -1.66
    酲
    -1.62
    agrad
    -1.54
    atég
    -1.52
     Subsequently
    -1.51
    ffiche
    -1.50
     clavier
    -1.50
    bánh
    -1.48
     akurat
    -1.48
     dieną
    -1.47
    POSITIVE LOGITS
     between
    2.47
    d
    2.03
     that
    1.87
     gap
    1.85
    "
    1.81
    t
    1.80
    c
    1.74
    gap
    1.74
    e
    1.73
    太大
    1.66
    Activations Density 0.036%

    No Known Activations