© 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. 19537
    Prev
    Next
    INDEX
    Explanations

    protected keyword in code

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     белая
    -1.96
     händer
    -1.95
     princí
    -1.95
     procesu
    -1.91
    setCellStyle
    -1.88
    蟊
    -1.85
    
    -1.85
     alkoholu
    -1.84
     pomen
    -1.84
    柺
    -1.83
    POSITIVE LOGITS
    ’
    2.91
    ’,
    2.58
    .’
    2.38
    However
    2.27
    4
    2.05
    .’’
    2.03
    3
    2.03
    Because
    2.00
    .”.
    1.99
    ”,
    1.98
    Activations Density 0.007%

    No Known Activations