© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 88718
    Prev
    Next
    INDEX
    Explanations

    checkmate**Reasoning:**- `MAX_ACTIVATING_TOKENS` contains "Check" and "Checks".- `TOKENS_AFTER_MAX_ACTIVATING_TOKEN` contains "mate" and "mates".- `TOP_ACTIVATING_TEXTS` frequently mentions "Check" and "Checkmate" in the context of chess.- The pattern is the combination of "Check" followed by "mate/mates", directly pointing to "checkmate"

    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_16_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
     decisive
    0.56
    一群
    0.48
     дори
    0.48
     =-
    0.48
     खरी
    0.46
     арифмети
    0.46
    "}
    0.46
     comprensión
    0.46
    <blockquote>
    0.46
    even
    0.46
    POSITIVE LOGITS
     eLearning
    0.53
     Container
    0.50
     Six
    0.49
     Curator
    0.48
    ENDER
    0.47
     Stop
    0.47
     Set
    0.47
     Tập
    0.46
     Sai
    0.46
     Blok
    0.46
    Activations Density 0.000%

    No Known Activations