© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11933
    Prev
    Next
    INDEX
    Explanations

    service provider

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

    The neuron fires strongly on occurrences of the standalone word “service.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kog
    0.70
     kog
    0.68
     DiCaprio
    0.66
     Rooster
    0.65
     Rossa
    0.65
    蠣
    0.64
    Harrison
    0.63
    roses
    0.63
     bip
    0.63
    蚪
    0.62
    POSITIVE LOGITS
     service
    1.24
    providers
    1.23
     providers
    1.22
     SERVICE
    1.21
     Service
    1.20
    服務
    1.20
     Providers
    1.19
     hizmet
    1.18
     серви
    1.14
     provider
    1.13
    Activations Density 0.160%

    No Known Activations