© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4768
    Prev
    Next
    INDEX
    Explanations

    therefore, followed by a comma

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

    The neuron fires on high-level discourse connectives that signal inference or transition (e.g. “Thus,” “So,” “Therefore”).

    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
    ор
    0.96
    tone
    0.95
    𝒶
    0.95
    са
    0.94
    म
    0.94
    ט
    0.91
    m
    0.91
    tops
    0.90
    times
    0.90
    ম
    0.89
    POSITIVE LOGITS
    才會
    0.88
     ஏற்பட்ட
    0.80
     gioc
    0.76
    ية
    0.76
    지와
    0.72
    氶
    0.71
    )<
    0.71
    たい
    0.70
    문에
    0.70
    í
    0.69
    Activations Density 0.034%

    No Known Activations