© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6572
    Prev
    Next
    INDEX
    Explanations

    code blocks and delimiters

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

    The neuron is triggered by ellipsis tokens (“...”), i.e. sequences of periods indicating omitted or trailing-off 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
    т
    1.07
    тли
    0.91
    на
    0.90
    ди
    0.82
    чка
    0.81
    й
    0.80
    _
    0.79
    ERNAL
    0.76
    y
    0.76
    чках
    0.75
    POSITIVE LOGITS
     But
    1.02
     🤔
    0.88
     nhưng
    0.88
    ।
    0.88
    แต่
    0.86
    लेकिन
    0.86
    ..?
    0.86
    。(
    0.86
     agak
    0.86
     但
    0.84
    Activations Density 0.082%

    No Known Activations