© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91806
    Prev
    Next
    INDEX
    Explanations

    online content creators and their platforms

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

    The neuron fires on high–information content tokens—especially numbers/dates, proper nouns, and topical keywords or headings.

    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
     製品
    -0.99
     необхід
    -0.84
    🍹
    -0.82
     fondue
    -0.81
     dawg
    -0.81
    👎
    -0.78
    (%)
    -0.78
     adal
    -0.77
     frites
    -0.77
    🍷
    -0.75
    POSITIVE LOGITS
     YouTube
    3.34
     influencer
    3.16
     YouTuber
    3.13
     influencers
    3.02
     Youtube
    2.80
     youtube
    2.80
     blogger
    2.67
    YouTube
    2.66
     TikTok
    2.45
    influ
    2.45
    Activations Density 0.059%

    No Known Activations