© 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. 116151
    Prev
    Next
    INDEX
    Explanations

    advertising campaigns

    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
    ஜ
    -0.90
    交易
    -0.84
    noten
    -0.83
    accessoires
    -0.79
    чают
    -0.77
    
    -0.77
    🆑
    -0.77
     remé
    -0.76
    mfenced
    -0.76
     laranja
    -0.76
    POSITIVE LOGITS
     campaign
    2.05
     campaigns
    1.82
     advertising
    1.81
     ads
    1.78
     Campaign
    1.56
     ad
    1.55
    campaign
    1.55
     targeting
    1.53
    Campaign
    1.48
     Ads
    1.41
    Activations Density 0.020%

    No Known Activations