© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73866
    Prev
    Next
    INDEX
    Explanations

    street names and numbers

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

    This neuron fires on capitalized multiword named entities—especially place names, street names, organizations, and person names.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     diminuer
    -1.23
     上衣
    -1.23
    formerly
    -1.18
     последний
    -1.16
    游戏的
    -1.14
    zijn
    -1.13
     jego
    -1.12
     ARISING
    -1.11
    gewä
    -1.11
    いたり
    -1.10
    POSITIVE LOGITS
     then
    2.00
     only
    1.82
     each
    1.68
     should
    1.66
     three
    1.60
     for
    1.59
     about
    1.53
     than
    1.51
     after
    1.48
     four
    1.48
    Activations Density 0.418%

    No Known Activations