© 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. 128036
    Prev
    Next
    INDEX
    Explanations

    access a SUMMARY

    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
    Not in Any Lists

    No Comments

    Negative Logits
    länge
    -1.22
     many
    -1.20
    salomon
    -1.17
     estampa
    -1.04
    manı
    -1.02
    время
    -1.01
    Հ
    -1.01
    ڧ
    -1.01
     adequate
    -1.00
    ਜ
    -1.00
    POSITIVE LOGITS
     detenidos
    1.43
    sistence
    1.20
    cio
    1.17
     venezolano
    1.13
     этого
    1.12
     that
    1.10
    usepackage
    1.09
     figliu
    1.09
     любы
    1.09
     diseñadores
    1.09
    Activations Density 0.004%

    No Known Activations