© 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. 15780
    Prev
    Next
    INDEX
    Explanations

    country Turkey and bird

    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
    ↵
    -2.59
    “
    -2.47
    pecabe
    -2.42
    饪
    -2.34
    苼
    -2.31
    。“
    -2.30
     -"
    -2.28
    檍
    -2.28
    </strong>
    -2.13
    zość
    -2.13
    POSITIVE LOGITS
    ;
    2.45
    ܜ
    2.23
    壜
    2.20
     將
    2.19
     将
    2.11
    緜
    2.09
    らん
    2.06
    кторов
    2.05
    鉭
    2.02
     於
    1.86
    Activations Density 0.004%

    No Known Activations