© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32289
    Prev
    Next
    INDEX
    Explanations

    Facebook Graph API SDK

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

    The neuron strongly activates on the literal token “Facebook,” i.e. whenever the Facebook brand name appears in the text.

    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
    小程序
    -0.76
     AssertionError
    -0.74
    Brush
    -0.73
    pués
    -0.73
    UOUS
    -0.72
     FRANC
    -0.71
    鱸
    -0.71
    随机
    -0.71
     COVERAGE
    -0.70
    Arms
    -0.70
    POSITIVE LOGITS
     Graph
    1.24
    graph
    1.13
     Connect
    1.02
     graph
    1.02
    connect
    0.98
    Graph
    0.98
    social
    0.93
     connect
    0.89
     Login
    0.88
    SDK
    0.84
    Activations Density 0.055%

    No Known Activations