© 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. 8665
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on semantically rich content words—especially longer nouns and adjectives—rather than on common function words.

    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
     ہوں۔
    0.75
    нибудь
    0.73
    wenn
    0.73
    或者是
    0.73
    もしくは
    0.73
    这样的
    0.72
     tramite
    0.71
    .
    0.71
     whichever
    0.70
    либо
    0.70
    POSITIVE LOGITS
     whereas
    1.08
     Whereas
    1.02
    していますが
    1.02
    但在
    0.99
     그런데
    0.91
     but
    0.91
     BUT
    0.91
     بينما
    0.88
    但是在
    0.88
     sedangkan
    0.86
    Activations Density 0.294%

    No Known Activations