© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8426
    Prev
    Next
    INDEX
    Explanations

    so followed by common words or abbreviations

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

    The neuron mainly detects occurrences of the word “so” (in any casing), especially when it appears in the “so‐called” construction.

    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_31_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
    쫑
    0.57
    Ճ
    0.56
    ப்பதற்காக
    0.55
     गर्मियों
    0.54
    ΠΑ
    0.53
    avamo
    0.53
    CRED
    0.52
    㴬
    0.51
     夏
    0.51
    кульп
    0.50
    POSITIVE LOGITS
    ei
    0.64
    ek
    0.61
    you
    0.61
    jate
    0.59
     তুমি
    0.58
    hoz
    0.58
    vá
    0.57
     unsolicited
    0.57
    good
    0.56
    jak
    0.55
    Activations Density 0.145%

    No Known Activations