© 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. 118919
    Prev
    Next
    INDEX
    Explanations

    filenames and scales

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

    opening curly braces in JSON data structures, particularly those with significant nesting depth.

    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
     parachoque
    -1.95
    鬭
    -1.87
    鼍
    -1.86
     magasiner
    -1.77
     już
    -1.75
    ſam
    -1.70
    komt
    -1.68
     distanza
    -1.67
     estadounid
    -1.67
    我们的
    -1.66
    POSITIVE LOGITS
     
    1.98
     appunto
    1.92
     such
    1.76
    THE
    1.56
     It
    1.56
    The
    1.52
     оно
    1.50
     in
    1.49
    ,,
    1.48
     всех
    1.48
    Activations Density 0.012%

    No Known Activations