© 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. 66232
    Prev
    Next
    INDEX
    Explanations

    electricity grid

    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
    ähle
    -0.72
    HF
    -0.71
    加油
    -0.69
    knex
    -0.68
    baum
    -0.68
    Feder
    -0.68
    FromJson
    -0.66
    ื่น
    -0.66
    owana
    -0.66
    тельность
    -0.66
    POSITIVE LOGITS
     grid
    2.47
     Grid
    2.03
    Grid
    2.00
     grids
    1.98
    grid
    1.94
    GRID
    1.59
    grids
    1.45
     GRID
    1.30
     lưới
    1.25
     electricity
    1.24
    Activations Density 0.045%

    No Known Activations