© 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-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 4186
    Prev
    Next
    INDEX
    Explanations

    horse racing events

    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_53_width_262k_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
     Person
    0.48
    謢
    0.44
     PSD
    0.43
     Elastic
    0.43
     StyleSheet
    0.42
     Técn
    0.42
     macOS
    0.42
     MOQ
    0.42
     PoE
    0.42
    蚩
    0.41
    POSITIVE LOGITS
     horses
    1.47
     racing
    1.38
     race
    1.26
     horse
    1.24
     races
    1.23
     raced
    1.23
     caballos
    1.22
     jockey
    1.21
    racing
    1.17
    horse
    1.13
    Activations Density 0.005%

    No Known Activations