© 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. 11716
    Prev
    Next
    INDEX
    Explanations

    multilingualism and functionality

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

    This neuron responds to structural reference tokens—things like section or page numbers, citation parentheses, headings, and other bibliographic or numbered markers.

    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
    だって
    1.02
     あなた
    0.91
     amost
    0.90
    ౖ
    0.89
    しない
    0.89
    ﻭ
    0.88
    りの
    0.88
     カーボン
    0.88
     Cũng
    0.88
     universitaria
    0.86
    POSITIVE LOGITS
    oled
    0.76
    ’,
    0.74
    els
    0.73
    ena
    0.73
    ellers
    0.73
    ,’
    0.72
     Predators
    0.71
     éléments
    0.71
     Dodson
    0.70
    🗓
    0.70
    Activations Density 0.000%

    No Known Activations