© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15278
    Prev
    Next
    INDEX
    Explanations

    racing cars and motorsport

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

    racing and motorsport concepts

    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_16k_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
     സ്ത്രീ
    0.59
    妇女
    0.59
    ⛹
    0.58
    Basketball
    0.54
    婦
    0.54
    図書館
    0.52
    ৩১
    0.51
    喤
    0.50
     สะ
    0.50
    🚶
    0.50
    POSITIVE LOGITS
     racing
    1.52
     motorsport
    1.49
     Racing
    1.32
     racer
    1.31
     Motorsport
    1.29
     racers
    1.27
    racing
    1.17
     FIA
    1.14
     race
    1.11
     NASCAR
    1.10
    Activations Density 0.163%

    No Known Activations