© 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. 75663
    Prev
    Next
    INDEX
    Explanations

    software platform and product names

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

    This neuron fires on individual tokens that are proper names or technical identifiers (e.g. software or organization names and model/version numbers).

    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
     zwłaszcza
    -1.13
    anwalt
    -1.10
     remarqu
    -1.08
    一共
    -1.07
     другому
    -1.05
    ◸
    -1.04
    tét
    -1.02
     нази
    -1.00
     serangan
    -1.00
    Elen
    -0.98
    POSITIVE LOGITS
     system
    1.87
     ecosystem
    1.76
     experience
    1.61
     family
    1.60
     team
    1.57
     approach
    1.55
     environment
    1.55
     method
    1.50
     website
    1.46
     process
    1.41
    Activations Density 0.353%

    No Known Activations