© 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. 12058
    Prev
    Next
    INDEX
    Explanations

    The neuron is principally triggered by tokens containing the substring “ing.”

    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
     Peloton
    0.89
     Sienna
    0.87
     NVIC
    0.81
    铺
    0.80
    ணிய
    0.78
    nten
    0.77
     Phần
    0.77
     GSH
    0.76
     smaller
    0.76
     NIO
    0.76
    POSITIVE LOGITS
    ੋ
    0.91
    '
    0.86
     radiographs
    0.79
     hooks
    0.75
    '%(
    0.72
     counterparts
    0.70
    lara
    0.70
    araja
    0.68
    Newly
    0.68
    :
    0.68
    Activations Density 0.000%

    No Known Activations