© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11917
    Prev
    Next
    INDEX
    Explanations

    package or module names

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

    periods (dots) in Java package names and import statements.

    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
     of
    -2.16
     география
    -1.52
     swojej
    -1.45
    te
    -1.42
     verdo
    -1.41
    ()
    -1.37
     WHOLE
    -1.36
     intval
    -1.36
     PERFECT
    -1.35
    liz
    -1.34
    POSITIVE LOGITS
     still
    1.73
    でしたが
    1.72
    ısından
    1.55
    acakt
    1.50
     comprised
    1.48
    They
    1.48
     but
    1.48
     three
    1.45
     に関する
    1.42
     noastre
    1.42
    Activations Density 0.046%

    No Known Activations