© 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. 10-GEMMASCOPE-RES-131K
    4. 48048
    Prev
    Next
    INDEX
    Explanations

    dark, dead, or alert and names

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

    The neuron is triggered by proper‐noun named entities—especially names of TV shows, networks, and personalities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </strong>
    -1.33
    gaven
    -1.22
    isku
    -1.13
    preso
    -1.12
     bahwa
    -1.12
    ,
    
    
    -1.10
     sở
    -1.06
    </h1>
    -1.06
     telev
    -1.06
    forKey
    -1.05
    POSITIVE LOGITS
     metų
    1.27
    是怎么回事
    1.26
    c
    1.20
    Nuorodos
    1.18
     moletom
    1.16
     להיות
    1.14
    θηκε
    1.13
    后
    1.13
    はない
    1.12
     нього
    1.10
    Activations Density 0.032%

    No Known Activations