© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104596
    Prev
    Next
    INDEX
    Explanations

    places and businesses

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

    This neuron activates on mentions of commercial establishments or retail businesses (e.g., grocery store, bank, shops, bars, restaurants).

    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
     during
    -1.59
     only
    -1.41
     it
    -1.36
     just
    -1.34
     use
    -1.33
     people
    -1.28
     problems
    -1.26
     even
    -1.22
     all
    -1.21
     especially
    -1.20
    POSITIVE LOGITS
     nyní
    1.55
     veículos
    1.32
     Pemain
    1.20
    humidité
    1.16
    licazione
    1.16
    头发
    1.15
     násled
    1.13
     duong
    1.12
    wonderful
    1.11
    unable
    1.11
    Activations Density 0.083%

    No Known Activations