© 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. 72229
    Prev
    Next
    INDEX
    Explanations

    OLED display technology

    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
     que
    -2.41
    ro
    -2.06
     However
    -1.98
    be
    -1.98
    </i>
    -1.95
    in
    -1.88
    向了
    -1.87
    いれば
    -1.84
     のか
    -1.82
     But
    -1.80
    POSITIVE LOGITS
     dotyczące
    1.98
     tiada
    1.97
    —
    1.89
    ;
    1.88
    ，”
    1.84
    慙
    1.84
     icône
    1.83
     kakak
    1.80
    栳
    1.76
     marqu
    1.75
    Activations Density 0.006%

    No Known Activations