© 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. 16-GEMMASCOPE-2-RES-262K
    7. 145489
    Prev
    Next
    INDEX
    Explanations

    aroused and excited

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    nn
    0.54
    yx
    0.48
    tour
    0.47
    ln
    0.46
    pR
    0.46
    f
    0.45
     separat
    0.45
    p
    0.45
    tl
    0.44
     CX
    0.44
    POSITIVE LOGITS
     adrift
    0.53
     mismos
    0.53
     anticipating
    0.52
     flagged
    0.50
     ተጨማሪ
    0.50
    ুহ
    0.49
     እንቅስቃሴ
    0.49
     stessi
    0.49
     squeezed
    0.47
     warned
    0.47
    Activations Density 0.000%

    No Known Activations