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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80747
    Prev
    Next
    INDEX
    Explanations

    packaging related to devices

    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
     entiende
    -0.74
    GRU
    -0.73
     increíbles
    -0.73
    接到
    -0.73
    kumpulan
    -0.72
     otomatig
    -0.71
    Risultati
    -0.70
    rational
    -0.69
     Kurt
    -0.69
    措
    -0.68
    POSITIVE LOGITS
     package
    3.06
     packages
    2.61
    package
    2.31
    Package
    2.20
     Package
    2.13
    PACKAGE
    2.05
     Packages
    2.03
    packages
    1.82
    Packages
    1.79
     PACKAGE
    1.73
    Activations Density 0.064%

    No Known Activations