© 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. 16099
    Prev
    Next
    INDEX
    Explanations

    summing numbers from 1 to 100

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

    The main thing this neuron does is identify occurrences of explicitly religious or biblical terminology.

    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
     polyurethane
    0.87
    الإ
    0.80
     Bankruptcy
    0.76
    வரு
    0.75
     infrared
    0.74
     inquire
    0.74
    郯
    0.74
     Tento
    0.73
    Під
    0.73
     感じ
    0.72
    POSITIVE LOGITS
    an
    0.87
    o
    0.82
    emois
    0.81
    er
    0.77
    ров
    0.73
     pais
    0.72
    tow
    0.71
     etmiş
    0.71
    grown
    0.71
    anud
    0.70
    Activations Density 0.000%

    No Known Activations