© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10741
    Prev
    Next
    INDEX
    Explanations

    smart appliance, smart contracts

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

    This neuron activates strongly on occurrences of the word “smart” (in any casing or as part of terms like “Smartphones”).

    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
     Cape
    0.56
    луб
    0.55
    رام
    0.54
     Mardi
    0.53
     NSC
    0.53
     په
    0.52
     நன்றாக
    0.52
     画
    0.52
    ⴼ
    0.52
     }^{[
    0.51
    POSITIVE LOGITS
     smart
    1.12
    Smart
    1.05
     smarter
    1.02
     Smart
    1.00
     smartest
    0.98
    smart
    0.98
    智能
    0.96
     स्मार्ट
    0.89
    聪明
    0.87
     смарт
    0.86
    Activations Density 0.122%

    No Known Activations