© 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. 24-GEMMASCOPE-2-RES-16K
    4. 7480
    Prev
    Next
    INDEX
    Explanations

    data, date, country, adding, resources

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

    This neuron fires on standalone capitalized first names that start entries in lists of arrest or voter‐registration records.

    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
     viper
    0.90
    ivasena
    0.86
     पढ़
    0.85
     AMOLED
    0.83
     pâte
    0.83
    쾰
    0.83
     OOP
    0.82
     EtOH
    0.82
    KURZBESCHREIBUNG
    0.82
     Конечно
    0.82
    POSITIVE LOGITS
    قال
    0.70
    প
    0.70
    ال
    0.67
    み
    0.63
    个
    0.63
     Constraints
    0.62
     Resources
    0.60
    牙
    0.60
    مث
    0.59
    З
    0.59
    Activations Density 0.002%

    No Known Activations