© 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. 4635
    Prev
    Next
    INDEX
    Explanations

    predictive suggestions

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

    The neuron is sensitive to high-level discourse/connective words (e.g. causal conjunctions like “because” or “therefore,” modals like “may,” and similar connectors).

    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
    ية
    0.80
    ৈত
    0.75
    ওয়ার
    0.73
    ']
    0.71
     flue
    0.71
     envo
    0.70
    ளாக
    0.70
    ।
    0.70
     launches
    0.69
     announc
    0.69
    POSITIVE LOGITS
     Онлайн
    0.86
     Questa
    0.79
    ื่อง
    0.77
    Etudes
    0.77
    års
    0.76
     이게
    0.76
    Questa
    0.76
    ИТ
    0.75
    ्यात
    0.75
    ితే
    0.75
    Activations Density 0.000%

    No Known Activations