© 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. 31-GEMMASCOPE-2-RES-262K
    7. 200121
    Prev
    Next
    INDEX
    Explanations

    looking, staring, or gazing

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    히려
    0.46
    ナソニック
    0.44
    Чтобы
    0.42
    iverse
    0.42
    会い
    0.40
    etermined
    0.39
     거고
    0.39
     discredit
    0.38
    त्याने
    0.38
    꿩
    0.38
    POSITIVE LOGITS
     Courier
    0.49
     stared
    0.47
     staring
    0.45
     Visual
    0.43
     gaze
    0.43
     Europ
    0.42
     stare
    0.42
     gazed
    0.42
     obserw
    0.41
     glance
    0.41
    Activations Density 0.001%

    No Known Activations