© 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. 10-GEMMASCOPE-RES-131K
    7. 104813
    Prev
    Next
    INDEX
    Explanations

    package names and library imports

    np_acts-logits-general · gemini-2.5-flash-lite

    Java package names, particularly those in import statements and package declarations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     for
    -1.85
    wavering
    -1.81
    intelligible
    -1.80
    bilan
    -1.73
     detenidos
    -1.71
    franch
    -1.70
     suceso
    -1.68
    遑
    -1.68
    mitsub
    -1.67
     are
    -1.66
    POSITIVE LOGITS
    er
    2.03
    #
    1.99
    You
    1.96
    ↵
    1.94
     (
    1.88
    man
    1.88
    .
    1.81
    re
    1.80
    Maybe
    1.77
    "
    1.77
    Activations Density 0.038%

    No Known Activations