© 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. 7775
    Prev
    Next
    INDEX
    Explanations

    common punctuation and conjunctions

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

    This neuron detects intense, first-person personal confessions or vivid autobiographical statements (often involving trauma or dramatic events).

    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
     ఇప్పటికే
    1.16
    Upcoming
    1.02
     upcoming
    0.94
     দিচ্ছে
    0.94
     দিচ্ছেন
    0.94
     ہیں
    0.94
    currently
    0.89
     আপাতত
    0.88
    Tomorrow
    0.88
     हैं
    0.87
    POSITIVE LOGITS
     وكانت
    1.73
     damals
    1.70
     était
    1.68
    當時
    1.66
    当时
    1.64
     buvo
    1.62
     وكان
    1.58
     ήταν
    1.54
     vardı
    1.52
     당시
    1.48
    Activations Density 0.966%

    No Known Activations