© 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. 58250
    Prev
    Next
    INDEX
    Explanations

    beginnings of sections or documents

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

    The neuron fires on the “-er” comparative suffix at the ends of words.

    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
    丝毫
    -2.02
     petits
    -2.02
    𓆏
    -1.94
    鼯
    -1.91
     douane
    -1.87
    鶫
    -1.86
    
    -1.81
    糨
    -1.76
     telles
    -1.76
     après
    -1.76
    POSITIVE LOGITS
    to
    2.16
     может
    2.08
    no
    1.95
     to
    1.93
    Because
    1.91
    To
    1.86
    lo
    1.83
    需要
    1.81
     which
    1.77
    because
    1.76
    Activations Density 0.002%

    No Known Activations