© 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. 33090
    Prev
    Next
    INDEX
    Explanations

    flag

    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
    巻
    -0.79
     unique
    -0.77
    чих
    -0.72
     white
    -0.70
    zepine
    -0.69
     Werkzeug
    -0.69
    合作
    -0.67
    xr
    -0.66
    遺跡
    -0.66
    菩提
    -0.64
    POSITIVE LOGITS
     flags
    1.05
     flag
    0.98
     Flag
    0.97
     Flags
    0.94
    Flag
    0.93
     indoors
    0.93
     indoor
    0.92
    Flags
    0.90
    flag
    0.90
    FLAGS
    0.88
    Activations Density 0.009%

    No Known Activations