© 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. 69293
    Prev
    Next
    INDEX
    Explanations

    Sharia and other laws

    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
    orsese
    -1.91
     This
    -1.84
     Як
    -1.73
    anyeol
    -1.67
     Как
    -1.65
    一说
    -1.64
        
    -1.63
     be
    -1.62
    広く
    -1.59
     или
    -1.58
    POSITIVE LOGITS
    '
    2.53
    on
    2.11
    V
    2.02
    O
    1.77
    C
    1.72
     trebui
    1.63
    R
    1.59
    ra
    1.59
    U
    1.53
     kwanza
    1.50
    Activations Density 0.002%

    No Known Activations