© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12040
    Prev
    Next
    INDEX
    Explanations

    Christian Gospel preachers

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

    The neuron selectively detects named entities—proper names of people, places, organizations, and events.

    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
     cocktail
    0.66
     martini
    0.60
     whiskey
    0.57
    స్కీ
    0.56
     salami
    0.56
     cooper
    0.55
    <0xCA>
    0.54
     neighborhood
    0.54
     दूं
    0.54
    剥
    0.53
    POSITIVE LOGITS
     Gospel
    1.16
     하나님
    1.11
     Evangelical
    1.11
     молит
    1.10
    福音
    1.10
     Theology
    1.08
     Adventist
    1.06
     gospel
    1.05
     evangelical
    1.05
     Prayer
    1.02
    Activations Density 0.373%

    No Known Activations