© 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. 117942
    Prev
    Next
    INDEX
    Explanations

    database server scripts

    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
     jenny
    -0.80
    fuk
    -0.79
    thereal
    -0.79
     Pty
    -0.75
    resents
    -0.75
    etate
    -0.71
    tares
    -0.71
    kv
    -0.70
    Uninstall
    -0.69
     plantilla
    -0.68
    POSITIVE LOGITS
    tisk
    0.83
    database
    0.81
    享受
    0.78
    Tên
    0.73
    iente
    0.72
     Database
    0.71
    伺
    0.71
     Server
    0.71
    数据库
    0.70
    Transparent
    0.70
    Activations Density 0.015%

    No Known Activations