© 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. 75255
    Prev
    Next
    INDEX
    Explanations

    words starting with lang

    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
    hilangan
    -2.98
    녘
    -2.97
    CurtirCurtir
    -2.95
    鹋
    -2.94
    鉺
    -2.86
    
    -2.73
    塍
    -2.72
    ?’
    -2.72
    灃
    -2.70
     ส์
    -2.67
    POSITIVE LOGITS
    \
    3.69
    ar
    3.30
    的
    3.28
    `
    3.28
    is
    3.23
    "
    3.19
    b
    3.17
    m
    3.02
     '
    3.02
    </td>
    3.02
    Activations Density 0.008%

    No Known Activations