© 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. 8535
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on decimal or floating-point numbers (numbers with a decimal component), such as financial figures or precise measurements.

    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
    figcaption
    0.74
     ماه
    0.70
    বে
    0.69
    colgroup
    0.68
     $(`.
    0.68
    UARY
    0.67
     लड़की
    0.66
    ▹
    0.66
     капу
    0.65
    ۱۲
    0.64
    POSITIVE LOGITS
    t
    0.82
    ﻪ
    0.81
    見
    0.79
    e
    0.76
    urt
    0.75
     personalmente
    0.75
     ਸਿੰ
    0.75
    ிருந்து
    0.74
     indestructible
    0.74
    ed
    0.73
    Activations Density 0.000%

    No Known Activations