© 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. 6701
    Prev
    Next
    INDEX
    Explanations

    automation, manipulation, logistics, equipment, ownership

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

    The neuron responds to capitalized words and phrases—titles, headings, and other named‐entity tokens.

    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
    。)
    0.67
    VOID
    0.66
    。」
    0.64
    。\
    0.63
    o
    0.61
     하여
    0.61
    。"
    0.60
    。。
    0.59
    ！)
    0.59
     unut
    0.58
    POSITIVE LOGITS
    ни
    0.72
     Specialists
    0.67
    のための
    0.65
    対策
    0.64
     syndrome
    0.63
     теория
    0.63
     specialists
    0.62
    চে
    0.61
    щика
    0.61
    éma
    0.60
    Activations Density 1.584%

    No Known Activations