© 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. 13646
    Prev
    Next
    INDEX
    Explanations

    Scandinavian countries and regions

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

    The main thing this neuron does is detect numeric measurements and technical specifications (quantities, pixel counts, percentages, etc.).

    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
    ᥱ
    0.89
     defe
    0.87
    ैटिन
    0.86
    শিংটন
    0.84
    enez
    0.83
    iores
    0.83
    ino
    0.82
     douleur
    0.82
     स्मारक
    0.82
    मारक
    0.81
    POSITIVE LOGITS
     Svens
    1.62
     Å
    1.59
     både
    1.52
     Andersson
    1.52
     Swedish
    1.48
     Sø
    1.48
     Uppsala
    1.48
     å
    1.47
     Gothenburg
    1.44
     Göteborg
    1.44
    Activations Density 0.217%

    No Known Activations