© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93129
    Prev
    Next
    INDEX
    Explanations

    WhatsApp and messaging apps

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     SMK
    -0.85
     Akismet
    -0.81
    htaccess
    -0.79
    becher
    -0.73
     tweeted
    -0.71
     alis
    -0.71
    Vegas
    -0.70
     Terkait
    -0.70
    Obama
    -0.70
     大学
    -0.69
    POSITIVE LOGITS
     WhatsApp
    4.53
    WhatsApp
    3.66
     Whatsapp
    3.64
     whatsapp
    3.44
    whatsapp
    3.23
    Whatsapp
    3.11
     Telegram
    2.11
    Telegram
    1.88
     messenger
    1.82
     Messenger
    1.81
    Activations Density 0.030%

    No Known Activations