© 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. 56740
    Prev
    Next
    INDEX
    Explanations

    locations following prepositions or commas

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

    The neuron is most strongly activated by numeric tokens—digits, amounts, dates, and other number-related text.

    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
     Puget
    -1.33
     Broward
    -1.27
    Winnipeg
    -1.11
     Saskatoon
    -1.09
    Auckland
    -1.05
    Minneapolis
    -1.02
     Schenectady
    -1.02
     Waikato
    -1.01
    Purdue
    -1.01
     Shropshire
    -1.01
    POSITIVE LOGITS
     Mt
    1.28
     Junction
    1.19
     Pleasant
    1.16
     Pine
    1.14
     Spring
    1.13
     Mount
    1.12
     Deer
    1.10
     Upper
    1.08
     Glen
    1.08
     towns
    1.07
    Activations Density 0.359%

    No Known Activations