© 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. 12156
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on tokens containing numeric characters or number-like values.

    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
    AGC
    0.82
     Eb
    0.80
     Agg
    0.78
    4
    0.77
     tyres
    0.74
     luft
    0.72
     Noch
    0.71
     Regen
    0.70
    1
    0.70
     aggreg
    0.69
    POSITIVE LOGITS
    <unused38>
    0.82
    ז
    0.79
    čia
    0.79
    周囲
    0.78
    Қ
    0.75
    ר
    0.74
    lihat
    0.72
    П
    0.72
    Ў
    0.72
    الأ
    0.72
    Activations Density 0.001%

    No Known Activations