© 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. 5744
    Prev
    Next
    INDEX
    Explanations

    call to action verbs

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

    The neuron strongly activates on list‐item markers—bullets, enumeration punctuation, and date tokens (e.g. months and numbered steps) that typically appear in ordered or bulleted lists.

    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
    etted
    0.60
     अग्र
    0.59
    
    0.58
    ⏪
    0.58
    ivered
    0.57
     претен
    0.57
    ﹂
    0.55
    欵
    0.54
    sized
    0.54
    -[#
    0.53
    POSITIVE LOGITS
     Bootstrap
    0.64
     Jun
    0.61
     Accordingly
    0.61
     Aug
    0.59
    Accordingly
    0.57
     Yarn
    0.57
     Filho
    0.56
     Consequently
    0.55
     juin
    0.54
     Monastery
    0.54
    Activations Density 0.046%

    No Known Activations