© 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. 65511
    Prev
    Next
    INDEX
    Explanations

    comparing things

    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
     Hammond
    -0.84
     definidos
    -0.81
     QLabel
    -0.81
     metade
    -0.77
     certainty
    -0.76
     Mosley
    -0.76
    jede
    -0.75
     judic
    -0.75
    Classical
    -0.75
     extracto
    -0.74
    POSITIVE LOGITS
     apples
    5.25
    apples
    4.28
     Apples
    3.97
    Apples
    3.67
     apple
    3.58
    apple
    3.05
     Apple
    2.81
    Apple
    2.50
    苹果
    2.47
     APPLE
    2.28
    Activations Density 0.038%

    No Known Activations