© 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. 499
    Prev
    Next
    INDEX
    Explanations

    The neuron consistently lights up on common function words (especially articles and prepositions, e.g. “the,” “a,” “for,” “of”).

    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
    iation
    0.38
    та
    0.37
    et
    0.35
    ை
    0.34
    ர்
    0.33
    ⿸
    0.32
    etel
    0.31
    ে
    0.31
    elling
    0.31
     함수
    0.31
    POSITIVE LOGITS
     mountains
    0.38
     meisten
    0.37
     proverbial
    0.37
     same
    0.35
     hills
    0.35
     realm
    0.33
     vicinity
    0.33
     foothills
    0.33
     jeweiligen
    0.33
     midst
    0.31
    Activations Density 2.407%

    No Known Activations