© 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. 9172
    Prev
    Next
    INDEX
    Explanations

    you are here

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

    This neuron fires on meta-text that directly addresses or orients the reader—phrases like “you’re on this page,” “if you’re reading this,” and similar second-person page-navigation cues.

    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
    Hochspringen
    0.64
    cienza
    0.58
    maximize
    0.51
    人間の
    0.51
    #,
    0.50
    pages
    0.49
     สํา
    0.49
     নিজে
    0.48
    fulfill
    0.47
     আত্মসম
    0.47
    POSITIVE LOGITS
     Taxes
    0.62
     তন্ম
    0.59
     taxes
    0.58
     Political
    0.57
     Ames
    0.57
     Taxation
    0.57
     Mugabe
    0.57
     Landry
    0.57
     Morrissey
    0.57
     দ্রব্য
    0.56
    Activations Density 0.000%

    No Known Activations