© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8071
    Prev
    Next
    INDEX
    Explanations

    John followed by a name or title

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron consistently fires on occurrences of the proper name “John.”

    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
    entry
    0.72
    其中的
    0.65
    \/}
    0.63
    수록
    0.61
    Entry
    0.59
     entry
    0.57
    懂
    0.57
    主播
    0.55
    Weblinks
    0.53
    其中
    0.53
    POSITIVE LOGITS
    nie
    1.10
    athan
    1.02
     XXIII
    0.91
    nies
    0.84
    hny
    0.76
     Baptist
    0.75
    athon
    0.73
     Cena
    0.73
    nym
    0.71
     thần
    0.69
    Activations Density 0.077%

    No Known Activations