© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5765
    Prev
    Next
    INDEX
    Explanations

    vue template code

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

    This neuron detects mentions of downloadable or viewable document references (e.g. “pdf,” “download,” “view,” citation tokens like “J.”).

    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
    銛
    0.80
    ג
    0.79
    ﻖ
    0.77
     syringe
    0.76
    多个
    0.74
    命中
    0.74
    உங்கள்
    0.73
    i
    0.72
     inlaid
    0.71
    有时候
    0.71
    POSITIVE LOGITS
     아니
    0.84
     Stad
    0.78
     Gianni
    0.77
     КА
    0.75
     accueillir
    0.74
    нин
    0.73
     ))->
    0.71
     Sega
    0.71
     preclude
    0.70
    approve
    0.69
    Activations Density 0.001%

    No Known Activations