© 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. 12317
    Prev
    Next
    INDEX
    Explanations

    quantify achievements, automation, leveraging

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

    The neuron selectively responds to words in their gerund or present-participle form ending in “-ing.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    gerunds (verb forms ending in "-ing") in technical or procedural contexts, particularly related to design, development, or creation processes.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    abstract, process-oriented terms denoting transformation, scale, or systemic conditions (often expressed as gerunds or nominalizations)

    oai_token-act-pair · gpt-5Triggered 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
    さまざ
    0.39
     successivement
    0.37
    ermanfaat
    0.36
    參数
    0.36
    ೫
    0.36
     нередко
    0.35
    OLYBD
    0.35
     promul
    0.34
     untersucht
    0.34
     hereafter
    0.34
    POSITIVE LOGITS
     ছিলোনা
    0.42
     আসলে
    0.39
     Max
    0.38
     Didn
    0.38
     Massive
    0.38
     একদম
    0.38
     কোন
    0.38
     Screenshots
    0.38
     Pronghorn
    0.37
     ήταν
    0.37
    Activations Density 0.000%

    No Known Activations