© 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. 7682
    Prev
    Next
    INDEX
    Explanations

    online usernames or handles

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

    The neuron is firing on author or editor signature tokens (usernames) in edit metadata.

    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
    。
    0.50
    ():
    0.49
     OÜ
    0.49
    ány
    0.47
    ());
    0.47
    (
    0.47
    fficial
    0.46
    ↵↵↵↵↵↵↵
    0.45
    ↵↵↵↵
    0.44
    zano
    0.44
    POSITIVE LOGITS
     autrefois
    0.48
     hybr
    0.43
     powst
    0.42
     zwe
    0.41
     aix
    0.41
     ruptura
    0.40
     gigantes
    0.39
     fascist
    0.39
     numele
    0.38
     pione
    0.38
    Activations Density 0.000%

    No Known Activations