© 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. 51468
    Prev
    Next
    INDEX
    Explanations

    fracking and shale gas

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

    fracking and geothermal operations

    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
     Offshore
    0.52
    船
    0.51
    海底
    0.50
    船舶
    0.49
    海上
    0.48
     海
    0.46
     ভাস
    0.46
    🚢
    0.46
     کشتی
    0.45
    🛳
    0.45
    POSITIVE LOGITS
     fracking
    0.60
     fracturing
    0.54
     Vermont
    0.53
     Connecticut
    0.51
     shale
    0.51
    Connecticut
    0.47
     tractors
    0.47
    Vermont
    0.46
     Utah
    0.46
     infiltrated
    0.45
    Activations Density 0.039%

    No Known Activations