© 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. 2641
    Prev
    Next
    INDEX
    Explanations

    website domain names

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

    This neuron detects URL domain tokens (e.g. top-level domain parts like “.gov”, “.edu”, “.org”, “.uk”, etc.).

    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
     أ
    0.75
     しかし
    0.73
     Tuttavia
    0.71
    ızlı
    0.69
     porém
    0.67
     díg
    0.67
     câble
    0.67
     可愛い
    0.66
     écrire
    0.66
     ulcers
    0.66
    POSITIVE LOGITS
    common
    0.77
    /~
    0.71
    /
    0.68
    (
    0.67
    Repost
    0.66
    ('%
    0.65
    international
    0.65
    :
    0.65
    new
    0.64
    ()!=
    0.64
    Activations Density 0.025%

    No Known Activations