© 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. 64381
    Prev
    Next
    INDEX
    Explanations

    brand names and specific terms

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

    The neuron spotlights tokens used in product descriptions—brand/model names and feature/specification words conveying a product’s attributes.

    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
     if
    -1.58
     other
    -1.58
     NSCoder
    -1.37
     some
    -1.35
     Einige
    -1.31
     mojej
    -1.30
     gerekli
    -1.29
     sometimes
    -1.29
     красивые
    -1.27
     algunos
    -1.26
    POSITIVE LOGITS
     your
    1.70
     omfatt
    1.48
     bruno
    1.30
     venter
    1.30
     bandung
    1.29
     sentra
    1.27
     bruin
    1.23
     vanil
    1.23
     jule
    1.23
     tricot
    1.23
    Activations Density 0.053%

    No Known Activations