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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 23890
    Prev
    Next
    INDEX
    Explanations

    area, building, house, located

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

    The neuron specializes in spotting tokens that occur in geographic‐relationship phrases—like “county seat” or “intersection of two major Interstate highways”—that describe a place’s administrative or transportation context.

    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
     help
    -1.58
     this
    -1.37
     receive
    -1.34
     examples
    -1.34
     if
    -1.34
    čnosti
    -1.25
     quick
    -1.24
     example
    -1.23
    ıştır
    -1.22
    特朗普
    -1.21
    POSITIVE LOGITS
     駅前
    1.35
     contextes
    1.34
     också
    1.27
     beso
    1.23
     perpé
    1.23
    把你
    1.23
     téléph
    1.20
     siè
    1.20
     véhic
    1.19
     travaillent
    1.18
    Activations Density 0.234%

    No Known Activations