© 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. 115719
    Prev
    Next
    INDEX
    Explanations

    words starting with "auto"

    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
    きち
    -0.87
    去掉
    -0.85
    PMS
    -0.77
    rH
    -0.77
    pV
    -0.76
    xv
    -0.75
    fk
    -0.75
    ều
    -0.75
    等你
    -0.74
    这也
    -0.73
    POSITIVE LOGITS
    auto
    1.42
     auto
    1.30
    bahn
    1.08
     Auto
    1.05
    Auto
    1.02
     авто
    0.96
    auf
    0.95
     AUTO
    0.95
    动的
    0.91
    exec
    0.90
    Activations Density 0.029%

    No Known Activations