© 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. 12894
    Prev
    Next
    INDEX
    Explanations

    mobile carriers and networks

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

    The neuron is triggered by numeric tokens and technical specification terms—especially things like network generations (e.g. “5G,” “4G”), signal bars, measurements, and similar digits‐based specs.

    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
     webcam
    0.70
     Webcam
    0.65
    🛋
    0.63
    登录
    0.62
    畈
    0.59
     コーヒー
    0.58
    ไม้
    0.57
     Bathroom
    0.56
    碚
    0.56
     fluores
    0.56
    POSITIVE LOGITS
     GSM
    1.87
    GSM
    1.59
     LTE
    1.45
     cellular
    1.42
     Vodafone
    1.42
     CDMA
    1.41
     Cellular
    1.37
     Airtel
    1.36
    gsm
    1.34
     Verizon
    1.29
    Activations Density 0.306%

    No Known Activations