© 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. 12206
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on high-register or prestige-laden words and phrases (e.g. “luxury,” “formal attire,” “NASA”) indicating notions of grandeur, formality, or high status.

    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
     relatively
    0.68
     Matters
    0.59
     yeter
    0.58
     infrequently
    0.57
     specifically
    0.56
    だけでなく
    0.56
     Blunt
    0.56
    扨
    0.55
     கிடைக்க
    0.54
     relativement
    0.54
    POSITIVE LOGITS
    similar
    1.16
    Similar
    1.15
     similaire
    1.10
     analogous
    1.08
    一样的
    1.06
     similar
    1.05
     ähn
    1.01
    like
    1.00
     giống
    1.00
    のような
    1.00
    Activations Density 1.127%

    No Known Activations