© 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. 4616
    Prev
    Next
    INDEX
    Explanations

    identifier or ID

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

    The neuron specializes in spotting document metadata labels followed by their numeric identifiers (e.g., “Item No.:”, “Number:”), i.e. structured identifier fields.

    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
    の名前
    0.73
    きたい
    0.68
    峹
    0.65
    émica
    0.64
    だけでなく
    0.64
    ුණ
    0.61
    cées
    0.60
    👫
    0.59
    ables
    0.59
    ustomed
    0.59
    POSITIVE LOGITS
    №
    1.03
     №
    0.90
     شماره
    0.86
     XRD
    0.83
     نمبر
    0.82
     LM
    0.75
    پ
    0.75
     ID
    0.75
     G
    0.74
     B
    0.73
    Activations Density 0.025%

    No Known Activations