© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19094
    Prev
    Next
    INDEX
    Explanations

    electricity and power plants

    np_acts-logits-general · gemini-2.5-flash-lite

    grid system load forecasting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    临床
    0.57
     İslam
    0.53
    设
    0.53
    橱
    0.52
    黟
    0.52
    燹
    0.52
    红色
    0.52
    砚
    0.51
     Transplantation
    0.50
     ön
    0.50
    POSITIVE LOGITS
     FERC
    0.82
    発電
    0.80
    電力
    0.76
    electricity
    0.75
     grid
    0.69
     megawatts
    0.69
    grid
    0.68
     electricity
    0.67
     renewables
    0.66
    grids
    0.65
    Activations Density 0.083%

    No Known Activations