© 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. 40950
    Prev
    Next
    INDEX
    Explanations

    links within parentheses

    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
    Not in Any Lists

    No Comments

    Negative Logits
    re
    0.49
    m
    0.46
    mén
    0.44
    ុំ
    0.44
    that
    0.44
    adiyah
    0.43
    th
    0.43
    ม
    0.43
    said
    0.42
    ím
    0.42
    POSITIVE LOGITS
     rivet
    0.46
     particulares
    0.46
    㗽
    0.46
     riten
    0.44
    ؔ
    0.44
     espl
    0.44
     rivets
    0.44
    やり
    0.43
    けた
    0.42
     estampado
    0.42
    Activations Density 0.252%

    No Known Activations