© 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. 22-GEMMASCOPE-RES-131K
    7. 16563
    Prev
    Next
    INDEX
    Explanations

    prior to

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

    This neuron responds to occurrences of the capitalized word “Prior,” as used to introduce background or earlier work.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ↵↵
    -3.52
    "
    -3.16
     “
    -2.56
     ‘
    -2.56
      
    -2.41
    en
    -2.38
     normalmente
    -2.30
    :
    -2.28
     t
    -2.25
    ’:
    -2.25
    POSITIVE LOGITS
     valentín
    3.00
    咘
    2.88
     anhänger
    2.73
     素描
    2.67
     sebelum
    2.66
    蟶
    2.66
     手绘
    2.63
    蘩
    2.61
     kağıdı
    2.58
    ㍉
    2.50
    Activations Density 0.018%

    No Known Activations