© 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. 9929
    Prev
    Next
    INDEX
    Explanations

    wince, shudder, cringe, braced

    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
    ,’
    -2.20
     (‘
    -2.14
     But
    -2.13
     Are
    -2.06
    仪式
    -2.03
    焄
    -1.98
    ⇰
    -1.95
     Whether
    -1.94
     Erhöhung
    -1.91
    玬
    -1.90
    POSITIVE LOGITS
     traditionelle
    2.08
    ’
    1.86
     totalmente
    1.83
     totalement
    1.80
    Ⴀ
    1.79
     sarebbe
    1.77
     новые
    1.73
    
    1.66
    .''
    1.65
    ạ
    1.64
    Activations Density 0.006%

    No Known Activations