© 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. 59138
    Prev
    Next
    INDEX
    Explanations

    grant or funding opportunities

    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
     APPROACH
    -1.01
    mycompany
    -0.94
     FORMAT
    -0.93
    ticion
    -0.93
     cambia
    -0.92
     sembla
    -0.91
     hongos
    -0.91
    Basta
    -0.91
    ковая
    -0.89
     feront
    -0.89
    POSITIVE LOGITS
     report
    1.78
     sheet
    1.45
     summary
    1.41
     information
    1.40
     description
    1.28
     statement
    1.28
     details
    1.26
    summary
    1.23
     overview
    1.23
     list
    1.19
    Activations Density 0.145%

    No Known Activations