© 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. 102303
    Prev
    Next
    INDEX
    Explanations

    migrations.operations

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

    opening square brackets in structured code or data files (particularly in lists, arrays, or JSON structures).

    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
    A
    -2.25
     so
    -2.13
    If
    -1.98
    *
    -1.96
    T
    -1.87
    $
    -1.85
    E
    -1.83
     there
    -1.81
    ly
    -1.80
    for
    -1.80
    POSITIVE LOGITS
     :</
    1.97
    `
    1.96
    
    1.95
    gerichte
    1.94
    鼋
    1.93
    "]();
    1.92
    ଢ
    1.87
    *</
    1.85
    鸲
    1.80
    HING
    1.79
    Activations Density 0.002%

    No Known Activations