© 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. 64425
    Prev
    Next
    INDEX
    Explanations

    solving equations and calculations

    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
     dayan
    -1.34
    8
    -1.29
     adet
    -1.23
    捗
    -1.23
    6
    -1.23
     kalem
    -1.20
    7
    -1.20
     Resmi
    -1.15
    Отзывы
    -1.13
     truk
    -1.12
    POSITIVE LOGITS
     ersche
    1.36
     erhöhen
    1.32
     negó
    1.25
    UALA
    1.23
     vermag
    1.20
     engraçado
    1.20
    gouv
    1.19
     verfü
    1.16
     theyre
    1.16
    toDouble
    1.15
    Activations Density 0.042%

    No Known Activations