© 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. 359
    Prev
    Next
    INDEX
    Explanations

    The neuron is basically firing on contentful, non-function words (i.e. less common lexical words) rather than on high-frequency “glue” 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
    _(
    0.29
     coval
    0.28
    )-(
    0.28
     myel
    0.28
     probed
    0.27
    tfrac
    0.27
    0.27
    であり
    0.26
    つの
    0.26
    骰
    0.26
    POSITIVE LOGITS
     LoginPage
    0.34
     Sitting
    0.34
     Practical
    0.33
     Frankly
    0.33
     お客様
    0.32
     উঠলো
    0.32
    Ltd
    0.32
    rible
    0.31
     Honestly
    0.31
     Achieving
    0.31
    Activations Density 0.000%

    No Known Activations