© 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. 104495
    Prev
    Next
    INDEX
    Explanations

    errors and error handling

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

    the period/dot character used for accessing struct fields or methods in Go 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
     because
    -2.13
     would
    -1.65
    vedades
    -1.59
     should
    -1.57
     with
    -1.55
    Our
    -1.52
    的那个
    -1.49
     showed
    -1.48
    したのが
    -1.45
    Tentang
    -1.43
    POSITIVE LOGITS
     erstaun
    1.77
    个
    1.77
    o
    1.77
     elegantly
    1.72
    ↵↵
    1.72
     delightfully
    1.69
     amazingly
    1.68
    <!--
    1.67
    在
    1.66
    桖
    1.66
    Activations Density 0.009%

    No Known Activations