© 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. 104142
    Prev
    Next
    INDEX
    Explanations

    code, names, and introductory phrases

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

    the scope resolution operator `::` in programming code.

    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
    ophageal
    -1.55
    )
    -1.54
    幸好
    -1.52
    ched
    -1.51
    咦
    -1.48
    >--}}
    -1.42
    昻
    -1.41
    佧
    -1.41
    WAUKEE
    -1.39
    rigated
    -1.39
    POSITIVE LOGITS
    ”
    2.02
     that
    1.80
     jahre
    1.77
     hängt
    1.70
     này
    1.63
    ↵
    1.62
     äusser
    1.57
     từ
    1.56
    ugeot
    1.53
     scheint
    1.53
    Activations Density 0.002%

    No Known Activations