© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11676
    Prev
    Next
    INDEX
    Explanations

    quotes and contractions

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

    The neuron is primarily firing on single-quote/apostrophe tokens in the text.

    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
    で
    0.87
    에서
    0.79
    వారు
    0.76
     ")[
    0.68
    ்ச்ச
    0.68
    야
    0.68
     ujung
    0.67
    س
    0.66
    在
    0.65
    ার
    0.65
    POSITIVE LOGITS
    Tis
    1.23
     ’
    1.10
    ’’’’
    0.97
    tis
    0.84
    bout
    0.79
    TIL
    0.79
    -‘
    0.78
    Til
    0.77
    --’
    0.77
     (’
    0.75
    Activations Density 0.219%

    No Known Activations