© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13509
    Prev
    Next
    INDEX
    Explanations

    The neuron responds strongly to numeral‐heavy tokens—that is, to strings containing numbers (e.g. “2191.6768”).

    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
    কথা
    0.78
     Rakyat
    0.71
    ە
    0.71
    लेरिया
    0.68
    ្នាំ
    0.68
    ্লাস
    0.67
    व्यों
    0.67
    泪
    0.66
    inę
    0.66
    㸮
    0.66
    POSITIVE LOGITS
    DU
    0.73
    Д
    0.68
     В
    0.67
    <0xE2>
    0.66
     Aj
    0.66
     ก
    0.65
    Aj
    0.65
    Es
    0.65
     sf
    0.65
    Tr
    0.64
    Activations Density 0.000%

    No Known Activations