© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73831
    Prev
    Next
    INDEX
    Explanations

    code block markers

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

    The neuron responds to long runs of whitespace characters (indentation) at the starts of lines.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ่ม
    -0.94
    Overwatch
    -0.90
     jeder
    -0.89
    Distrito
    -0.88
     in
    -0.86
    이며
    -0.85
    onInit
    -0.84
    の神
    -0.84
    mainwindow
    -0.83
    __":
    
    -0.81
    POSITIVE LOGITS
     Zoning
    1.02
     Β
    1.02
     Ν
    1.00
    jmu
    0.96
    lijke
    0.95
     Є
    0.93
     fazendo
    0.93
    }]$
    0.93
    
    0.93
    nosi
    0.92
    Activations Density 0.002%

    No Known Activations