© 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. 89932
    Prev
    Next
    INDEX
    Explanations

    charts and plots

    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
    और
    -0.82
    Ved
    -0.77
     Betsy
    -0.77
    staden
    -0.75
    <0xF1>
    -0.75
    سال
    -0.72
     mila
    -0.71
    翡翠
    -0.71
     UCB
    -0.71
    rungen
    -0.69
    POSITIVE LOGITS
     chart
    1.45
     Chart
    1.44
    chart
    1.22
    Chart
    1.20
     charts
    1.17
     CHART
    1.11
     legend
    1.08
    charts
    1.07
     plot
    1.06
    plot
    1.04
    Activations Density 0.063%

    No Known Activations