© 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. 109576
    Prev
    Next
    INDEX
    Explanations

    presentation mode, server, hotel, or index

    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
    2
    -1.32
    N
    -1.05
    7
    -1.05
    THE
    -1.04
    s
    -1.01
     spanning
    -1.00
    O
    -1.00
    UT
    -1.00
    co
    -0.99
    8
    -0.99
    POSITIVE LOGITS
    presentation
    1.65
     Presentation
    1.57
    Presentation
    1.57
     presentation
    1.48
     Presentations
    1.41
     PRESENTATION
    1.34
    resentation
    1.34
    presenter
    1.34
     présentation
    1.27
    Presenting
    1.27
    Activations Density 0.012%

    No Known Activations