© 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. 69275
    Prev
    Next
    INDEX
    Explanations

    proper names and technical terms

    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
    𖣘
    -3.39
    
    -3.28
    銠
    -3.22
    鷓
    -3.13
     vivido
    -3.11
    usstsein
    -3.08
    㩒
    -3.03
    憮
    -3.00
     剧照
    -2.89
    チュラル
    -2.81
    POSITIVE LOGITS
    .
    3.34
     `
    3.20
     
    3.16
     -
    3.03
    r
    2.98
    ar
    2.91
     /
    2.89
     The
    2.77
     $
    2.75
    G
    2.70
    Activations Density 0.033%

    No Known Activations