© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8188
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on standalone floating‐point number tokens (i.e. numeric values with decimal points).

    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
     kammam
    0.98
     sient
    0.82
     spokoj
    0.80
    잍
    0.80
    𝖺
    0.79
    txtbtn
    0.75
    hā
    0.74
    原理
    0.73
     ਉਹ
    0.73
    dye
    0.73
    POSITIVE LOGITS
    !
    0.72
     Batteries
    0.69
     DES
    0.68
     DO
    0.67
    با
    0.67
     notifications
    0.67
     elapsed
    0.63
    -
    0.63
    olah
    0.63
    این
    0.63
    Activations Density 0.001%

    No Known Activations