© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72342
    Prev
    Next
    INDEX
    Explanations

    Irving, Keene, people, places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    for
    -3.19
    2
    -3.11
    0
    -2.94
    3
    -2.58
    8
    -2.56
    ar
    -2.52
    气氛
    -2.50
    是真的
    -2.47
    槩
    -2.41
     новым
    -2.38
    POSITIVE LOGITS
    🩻
    2.41
    шила
    2.33
    ombang
    2.33
    ྂ
    2.31
    NDICE
    2.30
     mindless
    2.28
    俑
    2.28
    ﻂ
    2.22
    geführt
    2.22
    鸶
    2.20
    Activations Density 0.060%

    No Known Activations