© 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. 22-GEMMASCOPE-RES-131K
    7. 16653
    Prev
    Next
    INDEX
    Explanations

    various languages and symbols

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    的气息
    -1.26
     Viena
    -1.23
     Riproduzione
    -1.22
     Başkanı
    -1.20
     vinyle
    -1.19
     Grazie
    -1.16
     allan
    -1.15
     appétit
    -1.13
     castel
    -1.13
    ֻ
    -1.13
    POSITIVE LOGITS
    '
    1.34
     desemple
    1.33
     tolle
    1.10
    はもちろん
    1.09
     зависит
    1.09
    Fakta
    1.09
     will
    1.08
    は約
    1.04
     --
    1.02
     acompanhar
    1.01
    Activations Density 0.016%

    No Known Activations