© 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. 12-GEMMASCOPE-2-RES-16K
    7. 158
    Prev
    Next
    INDEX
    Explanations

    the following

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

    the word "the" appearing in definite article contexts before nouns.

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

    the neuron activates on content-bearing topical words—especially nouns and proper nouns that signal key subjects or entities.

    oai_token-act-pair · gpt-5-miniTriggered by @jyhe0408

    the neuron looks for marketing/advertising text, especially product descriptions that include numbers and pricing/data.

    oai_token-act-pair · gpt-5-nanoTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    s
    0.85
    此
    0.61
     vị
    0.61
    ती
    0.57
     Lưu
    0.56
    ﻒ
    0.55
     tròn
    0.55
    刘
    0.55
     Kt
    0.54
    етка
    0.54
    POSITIVE LOGITS
    ور
    0.63
    ro
    0.55
    ल
    0.54
    ورك
    0.52
    reiche
    0.51
    omsday
    0.50
     negeri
    0.50
    ،
    0.50
     paese
    0.49
    re
    0.49
    Activations Density 1.120%

    No Known Activations