© 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. 22-GEMMASCOPE-RES-131K
    4. 39954
    Prev
    Next
    INDEX
    Explanations

    social media pages or channels

    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_22/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
    Unless
    -1.31
    Either
    -1.28
     either
    -1.28
    7
    -1.27
    真的很
    -1.20
     Either
    -1.18
    either
    -1.17
     unless
    -1.14
    Any
    -1.13
    8
    -1.13
    POSITIVE LOGITS
     vinilo
    1.40
    ๗
    1.38
    槼
    1.36
     récemment
    1.30
    voer
    1.27
    ⎘
    1.26
     gorro
    1.20
     fabricación
    1.20
     boya
    1.20
    ってみました
    1.19
    Activations Density 0.015%

    No Known Activations