© 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. 98908
    Prev
    Next
    INDEX
    Explanations

    você ou user

    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
    Negative Logits
     felpa
    -1.42
    可能的
    -1.42
    右侧
    -1.38
     should
    -1.30
     project
    -1.26
    就好了
    -1.23
    花费
    -1.22
    iconductor
    -1.22
    ,”
    -1.19
     countries
    -1.18
    POSITIVE LOGITS
    queryInterface
    1.73
     fortsatt
    1.55
    </tfoot>
    1.52
    α
    1.52
    '];
    1.48
     først
    1.44
    apatalk
    1.39
    𝗖
    1.36
    只剩下
    1.34
    GraphicsUnit
    1.33
    Activations Density 0.015%

    No Known Activations