© 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. 2977
    Prev
    Next
    INDEX
    Explanations

    youtube links and URLs

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

    The neuron activates on colon punctuation (":"), marking places like “Q:” or section labels.

    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
    GetChar
    0.62
    Submit
    0.58
    AddTo
    0.57
    xadmin
    0.57
    Latin
    0.56
     வட்டம்
    0.56
    Possible
    0.55
    菽
    0.55
     व्यक्तियों
    0.54
    INFORMATION
    0.54
    POSITIVE LOGITS
     YouTube
    0.72
     Youtube
    0.72
     vidéos
    0.71
     YouTuber
    0.70
     youtube
    0.70
     YouT
    0.69
     Videos
    0.68
     videos
    0.66
     footage
    0.66
     videa
    0.65
    Activations Density 0.000%

    No Known Activations