© 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. 181874
    Prev
    Next
    INDEX
    Explanations

    car rental services and locations

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

    renting a car

    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
    URS
    0.45
     Aesthetic
    0.42
     Bier
    0.42
     Scheduler
    0.42
     antisense
    0.42
     bomber
    0.41
     Scheduling
    0.41
    𝑥
    0.41
     tumeurs
    0.40
    Scheduling
    0.40
    POSITIVE LOGITS
     автомоби
    0.72
    自動車
    0.70
     자동차
    0.66
    자동차
    0.64
    🚘
    0.64
     автомобі
    0.62
    🚙
    0.61
     автомобиль
    0.60
     automakers
    0.59
     Automobile
    0.58
    Activations Density 0.045%

    No Known Activations