© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 70111
    Prev
    Next
    INDEX
    Explanations

    image tags and attributes

    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_34/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
    mètre
    -0.78
     RFID
    -0.78
    ilane
    -0.76
     démoc
    -0.75
     Scrap
    -0.73
     onclick
    -0.73
    ソフトウェア
    -0.73
    btc
    -0.71
    Joyce
    -0.71
     Yue
    -0.71
    POSITIVE LOGITS
     lazy
    1.05
     sizes
    1.02
    lazy
    0.98
    sizes
    0.84
    Lazy
    0.83
     retina
    0.83
     placeholder
    0.79
    revalidate
    0.79
     Lazy
    0.77
    webp
    0.77
    Activations Density 0.015%

    No Known Activations