© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 777
    Prev
    Next
    INDEX
    Explanations

    currency symbols followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    The main thing this neuron does is identify numeric quantity expressions—especially monetary amounts and other measurements.

    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
     الإنسان
    0.35
    きます
    0.32
    творе
    0.31
    얽
    0.31
    者は
    0.31
    сматри
    0.30
    種
    0.29
    밖
    0.29
    Instit
    0.29
    Repositories
    0.29
    POSITIVE LOGITS
     $
    0.66
     £
    0.59
     ₹
    0.55
     ३
    0.54
     १५
    0.54
     whopping
    0.53
     ५
    0.52
     १०
    0.51
     five
    0.51
     €
    0.51
    Activations Density 0.211%

    No Known Activations