© 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. 49943
    Prev
    Next
    INDEX
    Explanations

    lists of actors and roles

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

    This neuron activates strongly on proper names of people (e.g. actors, directors) in cast or credits lists.

    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
    щества
    -0.82
     heiress
    -0.79
    cVar
    -0.78
    Aquatic
    -0.78
     evaluar
    -0.77
    cluso
    -0.76
     کردی
    -0.75
    Invisible
    -0.75
    标题
    -0.74
     fragrant
    -0.73
    POSITIVE LOGITS
     actors
    1.38
     actor
    1.22
    played
    1.14
     played
    1.08
     newcomer
    0.98
    actors
    0.96
     actriz
    0.95
     актер
    0.94
    casting
    0.93
     cast
    0.91
    Activations Density 0.041%

    No Known Activations