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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14147
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on Latin-derived filler text tokens (the “lorem ipsum” style words).

    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
    explode
    0.79
    ुप
    0.77
    consolid
    0.77
    mutex
    0.77
    notify
    0.77
    iegel
    0.76
    proud
    0.76
    o
    0.76
    club
    0.75
    eigen
    0.73
    POSITIVE LOGITS
    ，
    1.05
    它
    0.98
     postulated
    0.86
     ،
    0.80
     viruses
    0.80
    ،
    0.79
     ，
    0.76
     impossible
    0.76
    ри
    0.74
    рија
    0.74
    Activations Density 0.001%

    No Known Activations