© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6875
    Prev
    Next
    INDEX
    Explanations

    sports cars and racing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    錳
    0.46
     аў
    0.46
     Mikolai
    0.43
    एनएल
    0.42
     Medicaid
    0.41
    LOLL
    0.41
     посо
    0.41
     compassion
    0.41
     chlor
    0.40
     ্
    0.40
    POSITIVE LOGITS
     supercar
    0.83
     Porsche
    0.83
     motorsport
    0.78
     Ferrari
    0.76
     Motorsport
    0.73
    🏎
    0.70
    Porsche
    0.70
     racing
    0.68
     Racing
    0.67
     Lamborghini
    0.66
    Activations Density 0.151%

    No Known Activations