© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 37972
    Prev
    Next
    INDEX
    Explanations

    travel, wellness, awards, places

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

    The neuron fires on named entities—especially brand names, website or product names, awards, and other proper‐noun tokens.

    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
     tubes
    -0.85
     blocked
    -0.83
     Tubes
    -0.81
     Barbara
    -0.76
     Donald
    -0.73
     oldest
    -0.73
     durar
    -0.72
     activities
    -0.72
     University
    -0.72
     Columbia
    -0.70
    POSITIVE LOGITS
    Romance
    0.91
     lecteurs
    0.88
    SPA
    0.86
     équipements
    0.78
    punkte
    0.77
    廉
    0.76
    phans
    0.76
    readers
    0.75
    Comunic
    0.75
     verhe
    0.74
    Activations Density 0.005%

    No Known Activations