© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10455
    Prev
    Next
    INDEX
    Explanations

    just/simply/merely

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

    The main thing this neuron does is detect contentful, topic-relevant words (nouns, verbs, and other meaningful vocabulary) rather than common function words.

    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
     olmasına
    0.57
    িলারা
    0.54
     অনে
    0.52
    }}{
    0.50
    ﻅ
    0.50
    ्यू
    0.48
    でしょうか
    0.47
    纭
    0.47
    appelijke
    0.46
     একমাত্র
    0.46
    POSITIVE LOGITS
     just
    4.84
    just
    4.44
     JUST
    3.86
     simply
    3.78
    Just
    3.75
     Just
    3.70
     merely
    3.66
     просто
    3.64
     juste
    3.59
    simply
    3.47
    Activations Density 1.636%

    No Known Activations