© 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. 368
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens—especially decimal numbers conveying statistical or monetary values.

    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
     usu
    0.28
     обычно
    0.27
     relleno
    0.26
     toilette
    0.26
     idee
    0.25
     usually
    0.25
    })$.
    0.25
     mannitol
    0.25
     candied
    0.25
    讽
    0.25
    POSITIVE LOGITS
    د
    0.35
     총
    0.27
    zter
    0.26
     miliardi
    0.26
    ശാല
    0.26
     हज़ार
    0.25
     milioni
    0.25
    संख्य
    0.25
     ล้าน
    0.25
    אס
    0.25
    Activations Density 0.000%

    No Known Activations