© 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. 15973
    Prev
    Next
    INDEX
    Explanations

    online exchange platforms

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

    The neuron detects mentions of technical wiring diagrams (e.g. occurrences of “Wiring Diagram” or “Diagram” in that context).

    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
    пону
    0.65
     kilos
    0.60
    所在的
    0.60
     crowds
    0.57
    there
    0.56
     ‘
    0.54
    orders
    0.54
     آ
    0.53
    以为
    0.53
    পড়
    0.53
    POSITIVE LOGITS
     Wiring
    0.97
    Wiring
    0.89
     wiring
    0.89
    ケーブル
    0.88
     cabling
    0.86
     Grundlagen
    0.84
     Dateien
    0.84
     кабе
    0.83
     impianti
    0.82
     Cable
    0.82
    Activations Density 0.007%

    No Known Activations