© 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. 64318
    Prev
    Next
    INDEX
    Explanations

    units and quantities

    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
    ཥ
    -1.48
    泐
    -1.46
    の商品
    -1.37
    をしています
    -1.36
    ཊ
    -1.35
    の人は
    -1.35
    に行って
    -1.34
     camiones
    -1.34
     repuesto
    -1.34
     souple
    -1.32
    POSITIVE LOGITS
     during
    1.48
     because
    1.45
     while
    1.42
     despite
    1.39
     when
    1.38
     until
    1.29
     but
    1.28
     could
    1.27
     before
    1.24
    捗
    1.20
    Activations Density 0.016%

    No Known Activations