© 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. 6815
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to numeric tokens (digits or multi‐digit numbers) 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
     (-
    0.86
     (−
    0.81
     (
    0.79
     (=
    0.77
     ("
    0.75
     Crimea
    0.75
     During
    0.73
     동안
    0.71
     Uint
    0.71
     Alemania
    0.71
    POSITIVE LOGITS
    aujourd
    0.82
    自分で
    0.82
    social
    0.82
    yourself
    0.82
    ך
    0.79
    sites
    0.79
    書いて
    0.78
    just
    0.78
    expansive
    0.78
    Pourquoi
    0.77
    Activations Density 0.032%

    No Known Activations