© 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. 12197
    Prev
    Next
    INDEX
    Explanations

    The neuron detects floating-point numbers (decimal values) in the 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
    P
    0.94
    PAR
    0.82
    ifiably
    0.81
    U
    0.80
    L
    0.79
     Larkin
    0.79
    S
    0.78
    N
    0.77
    H
    0.74
     host
    0.74
    POSITIVE LOGITS
    но
    0.88
    ссо
    0.85
    আনু
    0.85
    ゎ
    0.84
    čních
    0.83
    ܠ
    0.83
     consequências
    0.80
    いない
    0.80
     süreç
    0.79
     ਸੀ
    0.79
    Activations Density 0.001%

    No Known Activations