© 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. 22-GEMMASCOPE-RES-131K
    7. 71750
    Prev
    Next
    INDEX
    Explanations

    web service requests and responses

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

    This neuron detects numeric literals (digits or numbers) 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_22/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
    EventName
    -0.99
     eventName
    -0.95
     Fieber
    -0.95
    atów
    -0.94
    IMEN
    -0.93
     quitté
    -0.91
    scribers
    -0.90
     поток
    -0.89
     gravidez
    -0.88
    Ů
    -0.86
    POSITIVE LOGITS
     json
    0.93
     ajax
    0.92
     request
    0.90
    json
    0.87
    Erfolge
    0.84
     القدس
    0.82
    Bissau
    0.82
     AJAX
    0.81
     response
    0.80
    requireNonNull
    0.79
    Activations Density 0.077%

    No Known Activations