© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129916
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on proper names and named entities (people, places, organizations) in news‐style text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    numbers and specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Not in Any Lists

    No Comments

    Negative Logits
     marvelous
    -1.75
     wondrous
    -1.66
     !!!!
    -1.64
     momentous
    -1.64
     olie
    -1.63
     Dinas
    -1.59
     relentless
    -1.56
     delightfully
    -1.56
     luscious
    -1.51
     .......
    -1.50
    POSITIVE LOGITS
     for
    1.80
     after
    1.80
     in
    1.79
     eight
    1.75
     on
    1.70
     enhances
    1.66
     three
    1.65
     six
    1.63
     four
    1.62
     five
    1.62
    Activations Density 0.042%

    No Known Activations