© 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. 23803
    Prev
    Next
    INDEX
    Explanations

    urban and rural areas

    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
     vettor
    -0.98
    ená
    -0.94
     certain
    -0.86
     halbe
    -0.85
     很
    -0.84
     alcuni
    -0.82
    に入って
    -0.82
     the
    -0.81
    すっ
    -0.80
     erwäh
    -0.78
    POSITIVE LOGITS
     areas
    3.22
     area
    3.09
    areas
    2.39
    area
    2.19
     Areas
    2.06
     área
    2.05
     áreas
    2.03
    Area
    2.00
     AREAS
    1.98
    Areas
    1.97
    Activations Density 0.034%

    No Known Activations