© 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. 15862
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on words naming physical structures or built spaces (e.g., storage, shop, workshop, barn, garage).

    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
    র
    0.77
     reflux
    0.75
     innocuous
    0.75
    ⓡ
    0.73
     flowed
    0.70
     流
    0.70
     flusso
    0.69
     turbidity
    0.69
     traiter
    0.67
     contamination
    0.66
    POSITIVE LOGITS
    或
    1.02
    শালী
    0.88
     یا
    0.86
    或者是
    0.86
    하거나
    0.86
    いたり
    0.84
     или
    0.82
     atau
    0.80
     किंवा
    0.80
     அல்லது
    0.79
    Activations Density 0.009%

    No Known Activations