Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7976
    Prev
    Next
    INDEX
    Explanations

    practice, policy, research, education

    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_34/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
     practice
    -2.67
    practice
    -2.33
     Practice
    -2.27
    Practice
    -2.20
    PRACTICE
    -2.00
     PRACTICE
    -1.97
     practices
    -1.91
     practicing
    -1.91
     practiced
    -1.90
     practise
    -1.83
    POSITIVE LOGITS
     beliefs
    0.87
     Anwendung
    0.83
     theory
    0.82
     sermon
    0.82
     setuptools
    0.78
     دليل
    0.76
     mệnh
    0.76
     thù
    0.74
     wskaz
    0.73
    ᐅ
    0.72
    Activations Density 0.024%

    No Known Activations