© 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. 116453
    Prev
    Next
    INDEX
    Explanations

    URLs and specific entities

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

    The neuron detects references to Amazon’s web domains (e.g., “amazon.com,” “amazon.es,” and their URLs).

    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
    rail
    -0.80
     proprie
    -0.79
     Medicina
    -0.79
    tipo
    -0.77
     tartalomajánló
    -0.75
     кров
    -0.73
    effic
    -0.72
    共产
    -0.72
     tipo
    -0.70
     there
    -0.70
    POSITIVE LOGITS
    gp
    1.91
    dp
    1.65
     gp
    1.38
    exec
    1.33
     dp
    1.09
    hz
    0.93
     exec
    0.90
     executives
    0.85
     executive
    0.83
    journal
    0.82
    Activations Density 0.005%

    No Known Activations