© 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. 10715
    Prev
    Next
    INDEX
    Explanations

    so [adjective describing degree]

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

    The neuron consistently activates on the intensifier “so.”

    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
     dość
    0.87
     좀
    0.79
     상당히
    0.78
     довольно
    0.77
    不错的
    0.77
    ك
    0.77
    ع
    0.76
     vrlo
    0.73
     bastante
    0.72
     زیادہ
    0.72
    POSITIVE LOGITS
     soooo
    0.82
    ledad
    0.81
     sooo
    0.80
    oooo
    0.72
     tellement
    0.70
    ว่า
    0.70
     kwamba
    0.66
    야
    0.66
     настолько
    0.65
     rằng
    0.64
    Activations Density 0.100%

    No Known Activations