© 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. 95559
    Prev
    Next
    INDEX
    Explanations

    I have

    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
     deren
    -1.03
     Customized
    -1.00
     even
    -0.98
    oczes
    -0.97
     Customization
    -0.94
    isUser
    -0.94
     Asymmetric
    -0.93
     customized
    -0.90
    mathrm
    -0.89
     chiar
    -0.88
    POSITIVE LOGITS
    ЗЫ
    1.10
     péro
    1.05
    мл
    1.05
    主要的
    1.01
    の特徴
    0.96
     jesús
    0.94
     韓国
    0.94
    なのでしょう
    0.93
    を変える
    0.91
    Besides
    0.91
    Activations Density 0.097%

    No Known Activations