© 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. 116410
    Prev
    Next
    INDEX
    Explanations

    social media platforms and sharing

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

    The main thing this neuron does is pick up numeric counts of social‐media engagement (e.g. share or subscriber numbers next to Facebook, Twitter, WhatsApp, etc.).

    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
     Facebook
    -2.08
    Facebook
    -2.02
     facebook
    -1.80
    facebook
    -1.77
    FACEBOOK
    -1.61
     FACEBOOK
    -1.52
    Liverpool
    -1.06
     Fb
    -1.01
     FB
    -1.00
    
    -0.92
    POSITIVE LOGITS
     Twitter
    1.27
     twitter
    1.23
     Instagram
    1.03
    twitter
    0.97
    Twitter
    0.96
     Pinterest
    0.90
     Google
    0.85
     tweets
    0.85
    instagram
    0.80
    ツイッター
    0.75
    Activations Density 0.021%

    No Known Activations