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. 196
    Prev
    Next
    INDEX
    Explanations

    trades and specialists

    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
     cheminée
    -2.45
    鸝
    -2.44
     poupée
    -2.42
    itoneum
    -2.39
    喾
    -2.28
     humeur
    -2.28
     âme
    -2.25
     poêle
    -2.25
    。“
    -2.23
     Güter
    -2.22
    POSITIVE LOGITS
    .
    2.91
    ↵↵
    2.53
     nebst
    2.02
     证书
    2.00
     "
    1.98
     We
    1.91
    なんですが
    1.91
    煐
    1.91
     plis
    1.88
     itp
    1.88
    Activations Density 0.003%

    No Known Activations