© 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-65K
    7. 55156
    Prev
    Next
    INDEX
    Explanations

    place values (tens, hundreds, thousands)

    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_65k_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
     evenly
    0.40
     Số
    0.38
     Balanced
    0.37
     Cloudy
    0.37
     açıkl
    0.35
     Suc
    0.35
     Sequences
    0.35
    臊
    0.35
     Maintenance
    0.35
    쩍
    0.35
    POSITIVE LOGITS
     tens
    1.09
    tens
    1.03
    Tens
    0.98
     hundreds
    0.94
     Tens
    0.88
     thousands
    0.86
     Hundreds
    0.83
    Hundreds
    0.82
    thousands
    0.81
     hundred
    0.80
    Activations Density 0.043%

    No Known Activations