© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 12661
    Prev
    Next
    INDEX
    Explanations

    touch grass or screen

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     कड़ी
    0.42
     あり
    0.41
     κό
    0.39
    ΤΑ
    0.38
    ONIUM
    0.38
     nourr
    0.38
     يأ
    0.38
    ojana
    0.37
    ៦
    0.37
    പ്പെട
    0.37
    POSITIVE LOGITS
     touch
    1.09
    Touch
    1.02
     touched
    1.02
     Touch
    1.01
    触
    0.93
    TOUCH
    0.92
    Touching
    0.91
     touching
    0.86
    触摸
    0.84
    touch
    0.84
    Activations Density 0.041%

    No Known Activations