© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9214
    Prev
    Next
    INDEX
    Explanations

    UI elements and drawing shapes

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

    The neuron specializes in spotting formatting or layout markup tokens (e.g. “separator” tags).

    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
     된
    0.66
     빈
    0.64
    ;')
    0.63
    ﻔ
    0.63
    ):
    0.62
     Wikidata
    0.62
    Է
    0.61
    된
    0.61
    研发
    0.60
     Yên
    0.60
    POSITIVE LOGITS
    iniai
    0.71
     které
    0.64
     które
    0.59
     jotka
    0.59
    />
    0.57
     ktoré
    0.57
    />}/>
    0.57
     entrances
    0.57
     типу
    0.57
     பிரச்சன
    0.56
    Activations Density 0.000%

    No Known Activations