© 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. 847
    Prev
    Next
    INDEX
    Explanations

    transnational and activation contexts

    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
    
    -2.98
     ferrovia
    -2.58
     The
    -2.53
    怱
    -2.50
    隳
    -2.47
    躄
    -2.42
     uſed
    -2.36
    🫅
    -2.28
    廛
    -2.27
     lauded
    -2.25
    POSITIVE LOGITS
    “
    3.44
    il
    2.50
    ↵
    2.38
    $
    2.19
    X
    2.16
    ,“
    2.14
    er
    2.13
    .”
    2.09
    R
    2.06
    E
    1.99
    Activations Density 0.003%

    No Known Activations