© 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. 13072
    Prev
    Next
    INDEX
    Explanations

    device hardware consumer

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

    The neuron fires on the key topic words or focal nouns that introduce or label each section (e.g. “space,” “feet,” “veggies,” “water,” “audio”).

    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
    棸
    0.72
     Сі
    0.71
    лаве
    0.70
     અંગે
    0.69
     কোলে
    0.68
    ใหญ่
    0.68
    ใหญ
    0.67
    
    0.66
     Microsc
    0.66
    要把
    0.66
    POSITIVE LOGITS
     slogans
    0.80
    y
    0.78
     whenever
    0.75
     ballots
    0.74
     zarówno
    0.74
     both
    0.72
     jederzeit
    0.70
    वादियों
    0.70
    ad
    0.69
    n
    0.69
    Activations Density 0.541%

    No Known Activations