© 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. 49963
    Prev
    Next
    INDEX
    Explanations

    fuel economy and efficiency

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

    fuel efficiency and consumption

    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
    鲢
    0.50
    踺
    0.47
    哏
    0.47
    手术
    0.46
     métall
    0.45
    负责人
    0.45
    锉
    0.45
    临床
    0.45
     खतरे
    0.45
     forceps
    0.44
    POSITIVE LOGITS
     energy
    0.92
     fuel
    0.88
     Energy
    0.86
    Energy
    0.85
     ENERGY
    0.84
     mpg
    0.84
    ENERGY
    0.82
    energy
    0.81
     Fuel
    0.77
    Fuel
    0.75
    Activations Density 0.054%

    No Known Activations