© 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. 106274
    Prev
    Next
    INDEX
    Explanations

    early Christian history

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

    The neuron fires strongly on numeric and date-related tokens (years, centuries, AD, page numbers, etc.).

    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
     Goethe
    -1.11
    ⍨
    -1.10
     newspaper
    -0.95
     satılık
    -0.95
    sierra
    -0.93
     electronic
    -0.93
    charlotte
    -0.92
    ΅
    -0.89
    lysses
    -0.88
     tervez
    -0.88
    POSITIVE LOGITS
    érée
    1.05
    early
    1.01
     marty
    0.97
     bishop
    0.91
     Fathers
    0.87
     Lact
    0.87
     Constantine
    0.87
     Euse
    0.86
     Emperor
    0.86
     converts
    0.86
    Activations Density 0.017%

    No Known Activations