© 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. 775
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on the standalone copula “is,” especially when it appears as the full word (e.g. in “This is…”).

    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
     tomto
    0.59
     meisten
    0.58
     acesta
    0.54
     BETWEEN
    0.52
    '.
    0.51
    '
    0.50
     diesem
    0.50
     هذا
    0.48
    哇
    0.47
     allí
    0.46
    POSITIVE LOGITS
     वजह
    0.61
    زش
    0.57
    clud
    0.55
    rifft
    0.55
     делается
    0.55
    ವಾದ
    0.55
    렇
    0.55
     ಪ್ರಶ್
    0.54
    les
    0.54
    あくまで
    0.54
    Activations Density 0.345%

    No Known Activations