© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65589
    Prev
    Next
    INDEX
    Explanations

    defence spokesperson colonel

    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
    mberg
    -0.81
     mascot
    -0.76
     ppm
    -0.73
    opers
    -0.73
    violi
    -0.72
    Amazon
    -0.71
     amazon
    -0.71
    apt
    -0.69
    าส
    -0.68
     fondos
    -0.68
    POSITIVE LOGITS
     Ministry
    1.97
    Ministry
    1.70
     MOD
    1.66
     Defence
    1.52
    MOD
    1.52
     Defense
    1.44
     ministry
    1.38
    Defence
    1.29
     defence
    1.23
     Ministries
    1.23
    Activations Density 0.048%

    No Known Activations