© 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. 110859
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

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

    sequences of digits, particularly in legal case citations and numerical identifiers.

    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
    𖣘
    -2.59
    liebte
    -2.17
    }{
    -1.94
    鱻
    -1.77
    咴
    -1.77
    ୈ
    -1.77
    ・・・・・
    -1.74
    几十
    -1.71
    imantan
    -1.71
    目前的
    -1.69
    POSITIVE LOGITS
    .
    2.73
     Now
    1.78
    ב
    1.70
    )=>{
    1.67
     Then
    1.67
    唻
    1.59
    人也
    1.59
     But
    1.59
    ↑↑↑</
    1.59
     Our
    1.58
    Activations Density 0.063%

    No Known Activations