© 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. 15767
    Prev
    Next
    INDEX
    Explanations

    military strategy and advice

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

    The neuron strongly activates on open‐class (content) words—i.e. nouns, verbs, adjectives, and other non–stop‐word 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
    颞
    0.76
    になると
    0.75
    たない
    0.73
    度は
    0.71
     Lucie
    0.71
    汚れ
    0.71
     نہیں
    0.68
    続
    0.68
    ریح
    0.67
    レンズ
    0.66
    POSITIVE LOGITS
     Zhao
    0.89
     Qian
    0.88
     hehe
    0.87
     hahaha
    0.86
     Qin
    0.85
     hắn
    0.84
     Zheng
    0.83
     Zhong
    0.83
     Jiang
    0.80
     Qing
    0.80
    Activations Density 0.062%

    No Known Activations