© 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. 24-GEMMASCOPE-2-RES-16K
    7. 12801
    Prev
    Next
    INDEX
    Explanations

    listing criteria and examples

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

    The neuron strongly flags colon characters (":"), effectively spotting list‐introducing or clause‐separating colons.

    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_24_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
    ."),
    0.56
    larından
    0.54
    overline
    0.52
    lerden
    0.52
     ],"
    0.52
    వాత
    0.52
     យើង
    0.52
    ভেন
    0.51
     beklen
    0.51
    ."],
    0.50
    POSITIVE LOGITS
    :
    0.56
    ؛
    0.56
     anggaran
    0.50
    јединачна
    0.49
     pelaksanaan
    0.48
    رياض
    0.48
    пуск
    0.47
    idoarjo
    0.47
    ﹔
    0.47
    ः
    0.47
    Activations Density 0.006%

    No Known Activations