© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7630
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
     steady
    0.54
     lidt
    0.50
     neighboring
    0.48
     roug
    0.48
     ¾
    0.48
     ten
    0.48
     Steady
    0.47
     twice
    0.47
    মুখী
    0.47
     똑
    0.46
    POSITIVE LOGITS
    超过
    2.38
     exceed
    2.23
     exceeding
    2.22
    超過
    2.20
     exceeds
    2.11
     exceeded
    1.98
     превы
    1.96
    低于
    1.86
    小于
    1.85
    เกิน
    1.82
    Activations Density 0.680%

    No Known Activations