© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34848
    Prev
    Next
    INDEX
    Explanations

    endpoint or endpoints

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

    The main thing this neuron does is detect mentions of “endpoint” (in any casing or pluralization).

    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
     Brilliant
    -0.84
     сва
    -0.80
    yorsunuz
    -0.79
    Brilliant
    -0.77
    OCOL
    -0.76
    tagne
    -0.73
    abonnement
    -0.72
    tifical
    -0.71
    xty
    -0.71
    čių
    -0.71
    POSITIVE LOGITS
     Endpoint
    0.87
     endpoint
    0.87
    endpoint
    0.84
    couverte
    0.78
    iken
    0.75
    endpoints
    0.75
    🐐
    0.75
    Endpoint
    0.75
    意義
    0.74
     BRON
    0.74
    Activations Density 0.004%

    No Known Activations