© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10976
    Prev
    Next
    INDEX
    Explanations

    URLs and phone numbers

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

    The neuron strongly activates on structured numeric sequences used in contact or booking details—especially phone numbers, prices, and web domains.

    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
    University
    0.72
    User
    0.69
    UserRepository
    0.67
    Faculty
    0.66
    Users
    0.65
    GoogleApiClient
    0.65
    [![
    0.64
    Unavailable
    0.64
    ViewHolder
    0.63
    ノ
    0.61
    POSITIVE LOGITS
     www
    1.17
    www
    0.83
     visit
    0.77
     descubre
    0.72
     Visit
    0.70
     événement
    0.70
     WWW
    0.68
     online
    0.67
     desempeño
    0.67
     quels
    0.66
    Activations Density 0.156%

    No Known Activations