© 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-65K
    7. 13509
    Prev
    Next
    INDEX
    Explanations

    phrases ending in specific words or punctuation

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     kanggo
    0.50
     учун
    0.48
     барои
    0.46
     !!!!
    0.45
     전류
    0.45
    මුත්
    0.44
     puriso
    0.44
    aparikkh
    0.44
     몇
    0.43
    для
    0.43
    POSITIVE LOGITS
     curated
    0.50
     omnichannel
    0.47
     undefined
    0.46
    local
    0.46
     GitLab
    0.46
    /
    0.46
     and
    0.45
    -
    0.44
     throughout
    0.44
     U
    0.43
    Activations Density 0.031%

    No Known Activations