© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59150
    Prev
    Next
    INDEX
    Explanations

    sustainability

    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
    皷
    -2.67
    痦
    -2.47
     Anſ
    -2.09
     giapponese
    -1.98
    壜
    -1.95
    雱
    -1.94
     rajut
    -1.93
    簠
    -1.91
    
    -1.90
    ᐠ
    -1.89
    POSITIVE LOGITS
    ;
    1.91
    K
    1.91
     for
    1.82
     of
    1.82
    呖
    1.79
    (
    1.72
     with
    1.69
    我们
    1.66
    เรา
    1.60
     con
    1.56
    Activations Density 0.012%

    No Known Activations