© 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. 41-GEMMASCOPE-2-RES-262K
    7. 63433
    Prev
    Next
    INDEX
    Explanations

    stock market crashes

    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_all/layer_41_width_262k_l0_big
    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
    HCR
    0.42
    Nay
    0.41
    nals
    0.40
     "????
    0.39
    Adri
    0.38
     resol
    0.37
     ರಾಜ
    0.37
     ({\
    0.37
     sidd
    0.37
     discrimin
    0.37
    POSITIVE LOGITS
     Crash
    0.67
    Crash
    0.63
     crash
    0.61
     crashes
    0.57
     crashed
    0.55
    crash
    0.50
     Cras
    0.50
     crashing
    0.47
     Winchester
    0.46
    🅔
    0.39
    Activations Density 0.001%

    No Known Activations