© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84873
    Prev
    Next
    INDEX
    Explanations

    meteor shower

    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
    razza
    -0.80
    वास
    -0.79
     Carmelo
    -0.75
     Taran
    -0.75
    birds
    -0.74
     Raza
    -0.73
     changes
    -0.73
     erleich
    -0.73
    iziert
    -0.72
     líquido
    -0.71
    POSITIVE LOGITS
     Perse
    1.18
     meteor
    1.16
     Meteor
    1.07
     mete
    0.99
    meteor
    0.98
     shower
    0.87
    Meteor
    0.85
    Synchron
    0.85
    shower
    0.82
     synchronized
    0.81
    Activations Density 0.054%

    No Known Activations