© 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. 3428
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting fragments of web URLs (e.g., “http,” “://,” domain parts, “.com,” etc.).

    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
    🚮
    0.58
    Dipl
    0.57
    페이스
    0.53
    ヒル
    0.52
     CMT
    0.52
     consulté
    0.52
    崂
    0.52
     दख
    0.52
    IMIENTO
    0.51
    もち
    0.51
    POSITIVE LOGITS
    andum
    0.59
     ២
    0.54
    othic
    0.53
     ጠ
    0.53
    aney
    0.52
    oxy
    0.50
     sympa
    0.50
    oil
    0.50
     समझ
    0.49
     দিয়েছিল
    0.49
    Activations Density 0.022%

    No Known Activations