© 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. 6975
    Prev
    Next
    INDEX
    Explanations

    romantic interest

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

    The neuron fires strongly on open‐class “content” words—i.e. nouns, verbs, adjectives, and adverbs carrying real semantic weight rather than on common function words.

    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
    做什么
    0.88
    ০
    0.80
    rophages
    0.78
    princip
    0.77
    ezi
    0.75
    nú
    0.75
    woven
    0.75
    readthedocs
    0.75
    do
    0.74
    Pepper
    0.74
    POSITIVE LOGITS
    ли
    0.76
    恼
    0.72
    ле
    0.70
     rumour
    0.70
     Lithuan
    0.68
     الماس
    0.68
     DMA
    0.66
     יד
    0.65
     Möglichkeit
    0.65
    謗
    0.65
    Activations Density 0.000%

    No Known Activations