© 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. 40-GEMMASCOPE-2-RES-262K
    7. 35304
    Prev
    Next
    INDEX
    Explanations

    currency amounts and approximations

    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_40_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
    百
    0.64
    三百
    0.61
    贰百
    0.57
    二百
    0.54
    一百
    0.47
     百
    0.47
     trăm
    0.44
     Hundred
    0.43
     १००
    0.42
     centena
    0.41
    POSITIVE LOGITS
     thousands
    1.16
     tens
    1.11
    Thousands
    1.00
    thousands
    0.99
    Tens
    0.95
     Thousands
    0.95
     Tens
    0.91
     हजारों
    0.88
    tens
    0.84
    萬
    0.83
    Activations Density 0.043%

    No Known Activations