© 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. 10-GEMMASCOPE-RES-131K
    4. 105044
    Prev
    Next
    INDEX
    Explanations

    the god of

    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
    ’
    -2.61
    同学们
    -1.73
     baskılı
    -1.71
     costuras
    -1.67
     $\&$
    -1.66
    时机
    -1.66
    傒
    -1.66
     blaue
    -1.66
    还有一
    -1.64
     ноябре
    -1.64
    POSITIVE LOGITS
     “
    2.02
     to
    1.99
     إذا
    1.87
    ',
    
    1.80
     beliebtesten
    1.74
    、“
    1.72
    XIII
    1.69
     мето
    1.63
    。“
    1.63
     selanjutnya
    1.63
    Activations Density 0.004%

    No Known Activations