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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 134
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ostavi
    -1.13
    店的
    -1.06
    erar
    -1.02
    سازی
    -1.02
    ('-'
    -1.00
    曩
    -0.99
    anın
    -0.98
    gage
    -0.98
    thodoxy
    -0.98
    ğun
    -0.96
    POSITIVE LOGITS
    It
    1.09
     have
    1.00
    しよう
    0.94
     financially
    0.94
    At
    0.92
    我
    0.92
     technically
    0.92
    “
    0.90
     ’
    0.90
     intellectually
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.