© 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. 83204
    Prev
    Next
    INDEX
    Explanations

    geological survey maps

    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
    ibrill
    -0.80
    ustris
    -0.77
    engar
    -0.74
     alugar
    -0.74
     operated
    -0.73
     found
    -0.73
     global
    -0.72
    =\
    -0.72
    ggs
    -0.71
     esetben
    -0.71
    POSITIVE LOGITS
     sheets
    1.01
     legenda
    0.94
     compilation
    0.92
    SHEET
    0.90
     legend
    0.89
    Digital
    0.88
    Mapped
    0.88
     capitaine
    0.87
    lanatory
    0.87
     map
    0.85
    Activations Density 0.011%

    No Known Activations