© 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. 22-GEMMASCOPE-RES-131K
    4. 484
    Prev
    Next
    INDEX
    Explanations

    sharing tweets on Twitter

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

    The neuron activates on mentions of tweets or tweeting, flagging references to people posting on Twitter.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     we
    -1.23
     our
    -1.20
    我们
    -1.06
     for
    -1.02
    hspace
    -0.94
    ğimiz
    -0.92
    -
    -0.90
    私たち
    -0.90
     must
    -0.89
     unserer
    -0.89
    POSITIVE LOGITS
     tweet
    1.83
     tweeted
    1.69
     Twitter
    1.59
     tweets
    1.55
     posts
    1.51
     posted
    1.41
     Tweet
    1.34
     twitter
    1.30
     FontWeight
    1.20
     tweeting
    1.19
    Activations Density 0.031%

    No Known Activations