© 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-262K
    7. 215659
    Prev
    Next
    INDEX
    Explanations

    explaining classification or definition

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     प्राथमिकता
    0.46
    جاب
    0.42
    一起
    0.40
    म्मा
    0.38
    де
    0.37
     आनंद
    0.37
    ร่วม
    0.37
    Người
    0.37
    煊
    0.37
    multiSelectList
    0.36
    POSITIVE LOGITS
     Phen
    0.45
     hvis
    0.43
     absurd
    0.42
     phenomen
    0.41
     trespass
    0.41
     schw
    0.40
     deduce
    0.40
     von
    0.40
     ricor
    0.40
     borderline
    0.39
    Activations Density 0.003%

    No Known Activations