© 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. 98903
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns

    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
    ’
    -4.03
     was
    -2.48
     '
    -2.47
     समीक्षाएं
    -2.47
    帳に追加
    -2.33
    erintah
    -2.30
    没有
    -2.28
     has
    -2.22
     This
    -2.22
     improbable
    -2.20
    POSITIVE LOGITS
    媄
    2.31
    幛
    2.27
    齷
    2.19
    .
    2.17
    to
    2.02
    手里的
    2.02
     positiven
    1.98
    塍
    1.98
    泐
    1.97
    ственного
    1.91
    Activations Density 0.004%

    No Known Activations