© 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. 77465
    Prev
    Next
    INDEX
    Explanations

    military operations and support

    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
    nóstico
    -0.85
    Пита
    -0.84
    編曲
    -0.80
    rogly
    -0.79
    Vehicles
    -0.78
    Sighs
    -0.77
    נטרנט
    -0.77
    اكم
    -0.77
    tổng
    -0.77
     diskusi
    -0.76
    POSITIVE LOGITS
     missions
    1.96
     support
    1.60
     duties
    1.46
     mission
    1.45
     tasks
    1.44
    Support
    1.38
     operations
    1.29
    Search
    1.27
     unterstützen
    1.26
    support
    1.19
    Activations Density 0.054%

    No Known Activations