© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13971
    Prev
    Next
    INDEX
    Explanations

    youtube URLs

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

    The neuron strongly activates on the alphanumeric segments of YouTube video URLs (i.e. the video ID tokens).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     коюм
    0.70
     CtApp
    0.64
    𝐫
    0.62
    ﻠ
    0.57
    Ꮃ
    0.57
    ETHOD
    0.56
    IFY
    0.55
     たい
    0.55
    Uy
    0.55
    alloween
    0.55
    POSITIVE LOGITS
     proteolytic
    0.61
     mo
    0.59
     encoded
    0.59
     cn
    0.59
     estrellas
    0.59
     por
    0.58
     messengers
    0.58
     acquisitions
    0.57
     dendritic
    0.57
     č
    0.56
    Activations Density 0.016%

    No Known Activations