© 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. 2194
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on specific product, company, or brand names.

    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
     pathophys
    0.57
    இர
    0.55
     druga
    0.54
     infrequently
    0.54
    こういう
    0.54
     ಸ್ವಲ್ಪ
    0.54
    膂
    0.53
     nDims
    0.52
     spineItem
    0.52
    㻴
    0.52
    POSITIVE LOGITS
    ®
    0.86
    ™
    0.82
     Ltd
    0.77
    ®,
    0.75
     GmbH
    0.73
    ®.
    0.69
    ℠
    0.68
     selaku
    0.67
     LLC
    0.66
     adlı
    0.64
    Activations Density 0.001%

    No Known Activations