© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49527
    Prev
    Next
    INDEX
    Explanations

    Municipal Airport, Court, Agency

    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
     又
    -0.91
    Hm
    -0.87
    phonie
    -0.87
    iksa
    -0.86
    DEPORT
    -0.85
    就要
    -0.82
    actéris
    -0.82
    厨师
    -0.82
    FAMIL
    -0.82
     grumpy
    -0.81
    POSITIVE LOGITS
    ITIES
    1.13
     corporations
    1.01
     corporation
    1.00
     governments
    0.97
     elections
    0.96
     bond
    0.95
     藏
    0.95
    ilty
    0.95
     coat
    0.93
    0.93
    Activations Density 0.010%
    No Known Activations