© 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. 8327
    Prev
    Next
    INDEX
    Explanations

    corporate financial performance

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

    This neuron responds to specific named entities, especially proper nouns like countries, cities, organizations, and technical system components.

    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
     nahin
    1.02
     บน
    1.01
    ik
    0.98
     T
    0.90
     Če
    0.89
     ওরফে
    0.88
     或
    0.87
     和
    0.86
     OÜ
    0.86
    ْر
    0.85
    POSITIVE LOGITS
    됬
    1.31
    recieve
    1.27
     recieved
    1.20
     পুনরায়
    1.13
     recieve
    1.07
     extremamente
    1.05
     bacterias
    1.01
    commision
    1.00
    countries
    0.99
     seperate
    0.98
    Activations Density 1.089%

    No Known Activations