© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10796
    Prev
    Next
    INDEX
    Explanations

    This neuron detects formal discourse markers and content words that introduce obligations, requirements, or hypothetical cases in explanatory or advisory text.

    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_24_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
     boyunca
    0.83
     wichtigsten
    0.82
    Además
    0.78
    すぐに
    0.77
    Invitrogen
    0.75
    ❥
    0.75
     კ
    0.74
    \|=\
    0.74
    َّة
    0.73
     fitur
    0.73
    POSITIVE LOGITS
     happenings
    0.90
     monies
    0.84
     expediency
    0.82
     situations
    0.81
     assorted
    0.81
     impediments
    0.81
    arbij
    0.81
     democracies
    0.80
    之事
    0.79
     circumstances
    0.76
    Activations Density 0.172%

    No Known Activations