© 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. 29244
    Prev
    Next
    INDEX
    Explanations

    oil and natural gas

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

    oil and gas industry

    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
    瓒
    0.63
     车
    0.61
    狯
    0.59
    妘
    0.59
    枫
    0.58
    校长
    0.57
    情节
    0.57
    表达
    0.57
     अंश
    0.57
    隐藏
    0.56
    POSITIVE LOGITS
     oil
    1.30
     drilling
    1.23
    oil
    1.16
    OIL
    1.16
    油
    1.14
     OIL
    1.13
     petroleum
    1.10
     offshore
    1.10
    石油
    1.09
     hydrocarbon
    1.09
    Activations Density 0.085%

    No Known Activations