© 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. 21926
    Prev
    Next
    INDEX
    Explanations

    HTML tags

    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
     or
    -3.14
     has
    -2.88
     any
    -2.52
     enticing
    -2.50
    !!
    -2.48
     impeccable
    -2.48
     multifaceted
    -2.48
     (
    -2.45
     unwavering
    -2.45
     unrelenting
    -2.39
    POSITIVE LOGITS
    𓆏
    3.63
    튿
    3.00
    킁
    3.00
    鹩
    2.95
    嵓
    2.94
     zoude
    2.89
    ఽ
    2.86
    鹟
    2.86
    ㍉
    2.81
    傒
    2.80
    Activations Density 0.004%

    No Known Activations