© 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. 80237
    Prev
    Next
    INDEX
    Explanations

    specific continuations after common words

    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
     be
    0.50
     censor
    0.46
    G
    0.44
    show
    0.43
     else
    0.43
    K
    0.42
    Commit
    0.42
     Anchor
    0.41
    ל
    0.41
     Generate
    0.41
    POSITIVE LOGITS
    kepsilon
    0.50
     étoiles
    0.50
     yoj
    0.49
    кового
    0.48
    滸
    0.48
     этим
    0.48
     ブリ
    0.48
     ফ্রি
    0.48
     ব্যাকটের
    0.48
    锴
    0.48
    Activations Density 0.001%

    No Known Activations