© 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. 400
    Prev
    Next
    INDEX
    Explanations

    heritage and conservation sites

    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
     избира
    -0.93
    大军
    -0.86
     Sea
    -0.82
     Chez
    -0.81
    YSTAL
    -0.80
    Chez
    -0.79
     wojsk
    -0.78
    IMUM
    -0.77
    SUITE
    -0.77
     physiology
    -0.77
    POSITIVE LOGITS
     heritage
    3.16
    Heritage
    2.55
     Heritage
    2.53
    heritage
    2.28
    Historic
    1.94
     UNESCO
    1.91
     preservation
    1.90
     conservation
    1.83
     Historic
    1.80
    ITAGE
    1.78
    Activations Density 0.062%

    No Known Activations