© 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. 5328
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on numeric references—step numbers, measurements, version codes, or other digits in technical/instructional text.

    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
    𝗙
    0.63
    estruct
    0.57
    伸縮
    0.55
    ες
    0.55
    isHorizontal
    0.55
    unarod
    0.55
     três
    0.54
    мін
    0.54
    доста
    0.54
     soluções
    0.54
    POSITIVE LOGITS
    <eos>
    2.20
    ៕
    1.11
     继续访问
    0.97
    </blockquote>
    0.75
    <start_of_image>
    0.74
    <unused63>
    0.70
    </tbody>
    0.69
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.62
    ↵↵↵↵↵↵↵
    0.62
    ↵↵↵
    0.61
    Activations Density 0.381%

    No Known Activations