© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100098
    Prev
    Next
    INDEX
    Explanations

    football defender

    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
    ',
    -1.63
    магазин
    -1.36
     econó
    -1.27
    帰り
    -1.26
    还想
    -1.19
     new
    -1.19
     User
    -1.16
     faudrait
    -1.16
     quizás
    -1.16
     Units
    -1.16
    POSITIVE LOGITS
     многое
    1.24
     سامسون
    1.23
    )’
    1.22
    中略
    1.22
    تمع
    1.22
     駅
    1.20
     Bikin
    1.20
    السلام
    1.16
     ボトル
    1.16
    ടെ
    1.16
    Activations Density 0.017%

    No Known Activations