© 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. 34792
    Prev
    Next
    INDEX
    Explanations

    watchdog

    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
    raujo
    -0.75
     displaced
    -0.75
    kilde
    -0.74
    Speed
    -0.74
     rękaw
    -0.73
     sushi
    -0.73
    ímetros
    -0.73
    ි
    -0.73
    NP
    -0.72
    enser
    -0.72
    POSITIVE LOGITS
     watchdog
    3.14
     Watch
    2.61
    watch
    2.53
     watch
    2.50
    Watch
    2.34
     WATCH
    2.06
    WATCH
    1.90
     watches
    1.81
     watched
    1.59
    dog
    1.42
    Activations Density 0.025%

    No Known Activations