© 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. 31-GEMMASCOPE-2-RES-16K
    7. 939
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting the special Unicode figure‐space token ( ).

    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_31_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
     ﺍﻟ
    0.75
    <unused2221>
    0.71
     بِ
    0.70
     ờ
    0.68
    <unused2164>
    0.68
     lewat
    0.65
    <unused99>
    0.64
    oretically
    0.64
     epigenetic
    0.63
     உருவாக்கு
    0.63
    POSITIVE LOGITS
    {#
    0.76
    {
    0.67
    See
    0.65
     noqa
    0.65
    ↵↵
    0.64
    Voir
    0.61
    This
    0.61
    also
    0.61
    WC
    0.60
     Targets
    0.59
    Activations Density 0.017%

    No Known Activations