© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5605
    Prev
    Next
    INDEX
    Explanations

    Facebook groups

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

    This neuron responds to mentions of online advertising platforms and related marketing metrics (e.g. Taboola, CPC, Facebook, content-distribution algorithms).

    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
     الخلي
    0.59
     Uranium
    0.59
    菇
    0.57
     Radiological
    0.57
     Cloudy
    0.56
    萝卜
    0.55
     lond
    0.55
    蘿
    0.55
     Wiley
    0.54
     Urinary
    0.54
    POSITIVE LOGITS
    Facebook
    2.20
     Facebook
    2.14
     facebook
    2.06
    facebook
    2.00
     FB
    1.96
     फेसबुक
    1.95
     fb
    1.91
     Fb
    1.91
    Fb
    1.80
    FB
    1.74
    Activations Density 0.296%

    No Known Activations