© 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. 110807
    Prev
    Next
    INDEX
    Explanations

    alert levels or threat conditions

    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
    uttgart
    -0.81
    šenie
    -0.75
    ക
    -0.75
     ravages
    -0.73
     insectic
    -0.71
    有时候
    -0.71
     една
    -0.71
     vertigo
    -0.71
     bestellt
    -0.70
     indistinct
    -0.69
    POSITIVE LOGITS
     alert
    3.20
    alert
    2.61
     Alert
    2.42
    Alert
    2.17
     alerts
    2.08
     alerta
    1.95
     Level
    1.80
     ALERT
    1.77
     yellow
    1.67
     advisory
    1.64
    Activations Density 0.032%

    No Known Activations