© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106726
    Prev
    Next
    INDEX
    Explanations

    data source repositories

    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_34/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
     gaya
    -0.72
    zegorz
    -0.71
    र्शन
    -0.70
     controles
    -0.69
     barriga
    -0.69
     ضد
    -0.69
    тива
    -0.69
    懑
    -0.69
     Hora
    -0.68
    ərb
    -0.68
    POSITIVE LOGITS
     repository
    1.47
    repository
    1.33
    Repository
    1.31
     dataSource
    1.23
     source
    1.20
    DataSource
    1.14
    datasource
    1.09
    source
    1.06
     Repository
    1.05
     sources
    1.02
    Activations Density 0.010%

    No Known Activations