© 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. 31-GEMMASCOPE-2-RES-16K
    7. 34
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting numeric tokens—especially sequences of digits and decimal 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_31_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
     🌱
    0.49
     🙌
    0.41
     cuddling
    0.41
     semakin
    0.41
     💞
    0.40
     méth
    0.40
     vielfält
    0.40
     fondness
    0.39
     ﺍﻟ
    0.39
    ḕ
    0.39
    POSITIVE LOGITS
    year
    0.46
    two
    0.46
    ↵↵
    0.46
    three
    0.45
    to
    0.43
    C
    0.42
    six
    0.40
    1
    0.40
    max
    0.39
    long
    0.39
    Activations Density 1.301%

    No Known Activations