© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7753
    Prev
    Next
    INDEX
    Explanations

    supercar brands

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

    sports car performance

    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_53_width_65k_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
    槎
    0.44
    Truck
    0.44
    pym
    0.43
    较大
    0.43
    舟
    0.42
    truck
    0.41
     washers
    0.41
    ⌀
    0.40
    嬸
    0.40
     মাঝি
    0.39
    POSITIVE LOGITS
     supercar
    1.48
     Ferrari
    1.30
     Lamborghini
    1.29
     McLaren
    1.21
    Ferrari
    1.13
     racing
    1.09
     exotic
    1.04
     Porsche
    1.04
     Maserati
    0.98
    Porsche
    0.96
    Activations Density 0.118%

    No Known Activations