© 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. 22566
    Prev
    Next
    INDEX
    Explanations

    natural gas and LNG shipping

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

    natural gas and methane

    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
    美术
    0.55
    皞
    0.54
    轶
    0.54
    咖啡
    0.52
    矾
    0.52
    睃
    0.51
    肾
    0.50
    细胞
    0.50
     커피
    0.49
     сахар
    0.49
    POSITIVE LOGITS
     gas
    1.42
     Gas
    1.22
    Gas
    1.20
     methane
    1.14
    gas
    1.13
     LNG
    1.09
     گاز
    1.09
     gás
    1.07
     propane
    1.06
     газо
    1.05
    Activations Density 0.085%

    No Known Activations