© 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. 127435
    Prev
    Next
    INDEX
    Explanations

    confirming research findings

    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
    \\
    -2.25
     если
    -2.17
     Here
    -2.11
    %
    -2.11
     "
    -1.99
    \'
    -1.88
     to
    -1.86
    汲
    -1.84
     jeśli
    -1.84
     You
    -1.79
    POSITIVE LOGITS
    喼
    2.33
    ”;
    2.16
    
    2.13
    卨
    2.06
    which
    2.05
    鲵
    2.03
    …”
    1.95
     rosse
    1.93
     北市
    1.90
     イラストレーション
    1.88
    Activations Density 0.014%

    No Known Activations