© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14411
    Prev
    Next
    INDEX
    Explanations

    nationalities

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

    The neuron fires strongly on capitalized named entities—proper nouns like place names, organization names, and other titles.

    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
     начинает
    0.59
     неожидан
    0.54
    𝘣
    0.52
     servent
    0.50
     adolesc
    0.50
    𝙠
    0.50
     demur
    0.49
    開封
    0.48
     アウトドア
    0.48
    プレゼ
    0.48
    POSITIVE LOGITS
    ब्ल्यू
    0.59
     जिक्र
    0.57
    rats
    0.57
    퀼
    0.55
    Typography
    0.54
     beanie
    0.54
    quartz
    0.52
    🧶
    0.52
     shawl
    0.52
     cuivre
    0.51
    Activations Density 2.278%

    No Known Activations