© 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. 239
    Prev
    Next
    INDEX
    Explanations

    The neuron detects nominalized action or process words—abstract nouns derived from verbs (e.g. implementation, disposal, conversion).

    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
    0
    0.46
    AlignCenter
    0.43
    ऊंगा
    0.41
    叔
    0.41
    한테
    0.40
    が出
    0.39
    もちゃ
    0.39
    ๐
    0.39
    0
    0.39
    ड्स
    0.38
    POSITIVE LOGITS
     của
    0.67
     of
    0.63
     ofthe
    0.59
     sürec
    0.58
     criteria
    0.56
     của
    0.55
     strategies
    0.53
     mechanisms
    0.53
     των
    0.52
    过程中
    0.51
    Activations Density 0.000%

    No Known Activations