© 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. 22875
    Prev
    Next
    INDEX
    Explanations

    condensed matter physics

    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
    produzione
    -1.82
     l
    -1.79
    titure
    -1.70
     revealed
    -1.63
     dahulu
    -1.63
    ');
    -1.53
    ).
    -1.52
     known
    -1.50
    omation
    -1.50
     различные
    -1.43
    POSITIVE LOGITS
    Tú
    1.73
    \
    1.72
     литературы
    1.65
     icône
    1.65
     всѣ
    1.58
    2
    1.51
     shimmer
    1.48
    虯
    1.45
    “
    1.45
    脔
    1.45
    Activations Density 0.001%

    No Known Activations