© 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. 34-GEMMASCOPE-RES-131K
    7. 1712
    Prev
    Next
    INDEX
    Explanations

    store customers

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

    This neuron fires on the structural markers of a news‐style dateline or headline—especially the em–dash and the capitalized location/title tokens that surround it.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Dining
    -0.96
     Dining
    -0.91
    chenke
    -0.88
     우리
    -0.88
     breeder
    -0.86
    нется
    -0.86
    ousal
    -0.85
     проєкту
    -0.84
     кухни
    -0.84
    ColElement
    -0.84
    POSITIVE LOGITS
     customers
    3.55
     customer
    2.95
     store
    2.78
     shop
    2.70
    Customers
    2.56
     Customers
    2.48
    customers
    2.44
     business
    2.17
    customer
    2.17
    store
    2.16
    Activations Density 0.064%

    No Known Activations