© 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. 7963
    Prev
    Next
    INDEX
    Explanations

    **"of" followed by "subsequent" or "extreme"**

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on morphologically marked content words—especially past‐tense or past‐participle verbs and nouns derived from verbs.

    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
     وعلى
    0.80
    ie
    0.78
     скульп
    0.74
    hmen
    0.71
    id
    0.68
    สาน
    0.66
     pw
    0.65
    ી
    0.65
    i
    0.64
    ortheast
    0.63
    POSITIVE LOGITS
     Polaribacter
    1.02
     Anakin
    0.89
     downregulated
    0.89
     Kval
    0.89
    плата
    0.86
    𐱅
    0.83
     kvalit
    0.83
     Berlusconi
    0.81
    درا
    0.80
     subtiliter
    0.80
    Activations Density 0.000%

    No Known Activations