© 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. 11200
    Prev
    Next
    INDEX
    Explanations

    list endings

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

    This neuron responds strongly to the abbreviation “etc” (and similar list‐continuation markers).

    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
     ನಿ
    0.57
    这两
    0.57
    ан
    0.54
    ←
    0.53
    ಚಿತ
    0.51
    secretary
    0.51
    ັ້ງ
    0.48
    section
    0.47
    clar
    0.47
    Illustration
    0.47
    POSITIVE LOGITS
    etera
    1.51
    etc
    0.95
    ..,
    0.94
    등
    0.94
     etcétera
    0.92
    …,
    0.91
    ...),
    0.89
     Etc
    0.84
     sebagainya
    0.84
     тощо
    0.81
    Activations Density 0.093%

    No Known Activations