© 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. 107229
    Prev
    Next
    INDEX
    Explanations

    external services and integrations

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

    This neuron responds to mentions of external integrations or services (e.g. component names like “External Services” or actions like linking a Facebook account).

    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
    Wert
    -0.76
    WAP
    -0.75
    Charlotte
    -0.75
     CHRIST
    -0.75
    Sziasztok
    -0.73
     Christ
    -0.72
    alucía
    -0.72
     tablette
    -0.72
    romeda
    -0.72
    SearchBar
    -0.71
    POSITIVE LOGITS
     connect
    2.02
     connected
    1.91
     connection
    1.77
     connects
    1.75
     connections
    1.69
    connect
    1.66
     connecting
    1.66
     integration
    1.59
     integrations
    1.55
    Connect
    1.53
    Activations Density 0.040%

    No Known Activations