© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31581
    Prev
    Next
    INDEX
    Explanations

    wifi connectivity

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

    The neuron specializes in detecting standalone numeric tokens (numbers).

    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
     CACHE
    -0.75
     partially
    -0.68
    Usb
    -0.66
    pleft
    -0.65
     kesi
    -0.64
     coke
    -0.63
    publicKey
    -0.63
     Cordero
    -0.63
     kotor
    -0.63
    grpc
    -0.61
    POSITIVE LOGITS
     WiFi
    1.20
     WIFI
    1.08
     wifi
    1.06
     Wifi
    1.02
     Wi
    1.00
     WLAN
    0.99
     OTA
    0.99
     STA
    0.99
     ESP
    0.98
    STA
    0.93
    Activations Density 0.023%

    No Known Activations