© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3353
    Prev
    Next
    INDEX
    Explanations

    cellular LTE modem broadband

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

    This neuron detects technical hardware and network-generation specifications—tokens like “3G,” “data card,” “single-mode,” “multi-mode,” “USB Wi-Fi router,” etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     discussing
    -0.75
     froze
    -0.74
     uninsured
    -0.73
     spoon
    -0.72
    fect
    -0.71
    ahora
    -0.71
     handleMessage
    -0.70
     rồng
    -0.69
     junior
    -0.69
    vamos
    -0.69
    POSITIVE LOGITS
     cellular
    1.42
     LTE
    1.27
     SIM
    1.23
     Cellular
    1.18
    cellular
    1.13
    Cellular
    1.13
    LTE
    1.13
    SIM
    1.10
     lte
    1.02
     Insee
    0.92
    Activations Density 0.036%

    No Known Activations