© 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. 53-GEMMASCOPE-2-RES-262K
    7. 12781
    Prev
    Next
    INDEX
    Explanations

    Chinese mythology, dragons, celestial phenomena

    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
    滏
    0.41
     Suez
    0.40
    銥
    0.40
    劻
    0.40
    揩
    0.39
    嚶
    0.39
     Ayrshire
    0.39
    Pink
    0.38
    許多
    0.38
    挼
    0.38
    POSITIVE LOGITS
     dragon
    0.52
     dragons
    0.46
     demon
    0.46
     Dragon
    0.44
    uldron
    0.43
     jade
    0.42
     spirit
    0.42
     calamity
    0.42
    柄
    0.42
    bolts
    0.42
    Activations Density 0.008%

    No Known Activations