© 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. 65946
    Prev
    Next
    INDEX
    Explanations

    research and analysis techniques

    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
    clerview
    -1.05
     basically
    -0.84
     dynamically
    -0.83
    kawi
    -0.82
    eroen
    -0.81
     outros
    -0.81
    板块
    -0.79
    variables
    -0.78
     politique
    -0.78
     graphically
    -0.78
    POSITIVE LOGITS
    числи
    1.19
    TRACT
    1.00
     tools
    1.00
    щается
    0.98
    блемы
    0.91
    ---+
    0.89
    рока
    0.88
    詈
    0.87
    subequations
    0.87
     techniques
    0.85
    Activations Density 0.182%

    No Known Activations