© 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. 8225
    Prev
    Next
    INDEX
    Explanations

    programming or code snippets

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

    This neuron responds strongly to colon punctuation (":"), i.e. locations of colons used to separate labels, headings, or list items.

    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
    :
    1.33
    ::
    0.95
    (
    0.91
    -
    0.84
    之中
    0.82
    :“
    0.81
    :|
    0.80
    [
    0.80
    |
    0.78
    :&
    0.78
    POSITIVE LOGITS
     PropTypes
    1.01
     Eine
    0.91
     een
    0.90
     Một
    0.90
    dokkaHtml
    0.90
     Sebuah
    0.90
     Its
    0.89
     onze
    0.88
     eine
    0.87
     一个
    0.86
    Activations Density 0.181%

    No Known Activations