© 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. 83343
    Prev
    Next
    INDEX
    Explanations

    violent storm

    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
    暑い
    -0.96
     heat
    -0.94
     sunflowers
    -0.93
    Suns
    -0.85
     verano
    -0.84
     summers
    -0.83
     sun
    -0.83
     Suns
    -0.80
     mosquitoes
    -0.80
     Hitze
    -0.79
    POSITIVE LOGITS
     winter
    1.35
     Winter
    1.13
     storm
    1.13
    winter
    1.12
    Winter
    1.10
    魁
    0.98
    storm
    0.98
     December
    0.98
     January
    0.95
     WINTER
    0.93
    Activations Density 0.011%

    No Known Activations