© 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. 345
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to numeric tokens or multi‐digit numeral sequences 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
    ançois
    0.42
    प्टेंबर
    0.42
    ेंद्रीय
    0.40
     आरमारा
    0.40
    ênd
    0.40
    raines
    0.38
    blers
    0.38
    Ḵ
    0.38
    ONY
    0.38
     जलाश
    0.38
    POSITIVE LOGITS
    0.44
     //
    0.40
    ::
    0.40
    0.38
     /*
    0.38
     quickSort
    0.36
     isValid
    0.36
    //
    0.35
     ||
    0.35
     $"{
    0.35
    Activations Density 0.025%

    No Known Activations