© 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. 10-GEMMASCOPE-RES-131K
    7. 47462
    Prev
    Next
    INDEX
    Explanations

    religious scriptures

    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_10/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
    潆
    -2.55
    
    -2.50
    谞
    -2.47
    戋
    -2.44
    䊏
    -2.33
     trám
    -2.30
    Sekarang
    -2.28
    7
    -2.25
    Semoga
    -2.25
    吖
    -2.22
    POSITIVE LOGITS
    ↵↵
    2.72
    B
    2.28
    <strong>
    2.13
    .
    2.11
    D
    1.98
    mathrm
    1.95
    ar
    1.94
    <i>
    1.93
    S
    1.92
    H
    1.91
    Activations Density 0.006%

    No Known Activations