© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2451
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is spot numerical quantities or measurements (numbers and their associated units or counts).

    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
    屢
    0.62
     ხელ
    0.61
     noreferrer
    0.59
    呛
    0.59
     पल
    0.58
     घायल
    0.57
     주변
    0.54
    飄
    0.54
    游
    0.53
     tận
    0.52
    POSITIVE LOGITS
     divided
    2.72
    分成
    2.64
    分为
    2.63
    divided
    2.58
    分為
    2.58
     divide
    2.55
     تقسیم
    2.55
     divides
    2.52
     dibagi
    2.50
     suddiv
    2.50
    Activations Density 0.759%

    No Known Activations