© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 87174
    Prev
    Next
    INDEX
    Explanations

    online communities and social sites

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

    This neuron fires on document‐structural tokens—things like numbers, punctuation, separators (e.g. “======”), and HTML tags.

    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
     millennials
    -1.36
     $"{
    -1.33
     emojis
    -1.23
     TikTok
    -1.21
     Whatsapp
    -1.20
    WhatsApp
    -1.19
     YouTuber
    -1.17
    ​​​​​​​
    -1.16
     Brexit
    -1.12
    ӓ
    -1.12
    POSITIVE LOGITS
     users
    1.38
     idéia
    1.34
     user
    1.23
     nutrientes
    1.15
     site
    1.02
     community
    1.00
     richer
    1.00
     social
    1.00
     mecanismos
    1.00
     comunidades
    0.99
    Activations Density 0.236%

    No Known Activations