© 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. 35798
    Prev
    Next
    INDEX
    Explanations

    occlusion, websites by

    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
     our
    -1.54
     those
    -1.31
     we
    -1.23
    脘
    -1.10
     смарт
    -1.08
     гита
    -1.08
     clients
    -1.07
     now
    -1.07
    hander
    -1.06
     what
    -1.05
    POSITIVE LOGITS
     chré
    1.48
    imakasih
    1.45
     religieux
    1.42
    Mvh
    1.42
     katholischen
    1.39
    bước
    1.27
     概要
    1.27
    Filmografia
    1.25
     your
    1.21
    上涨
    1.20
    Activations Density 0.011%

    No Known Activations