© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86517
    Prev
    Next
    INDEX
    Explanations

    initials followed by names or codes

    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
     That
    -3.14
    ....
    -2.98
    ڧ
    -2.88
    .......
    -2.78
    ⸒
    -2.72
    
    -2.70
     exquisitely
    -2.69
    𓄹
    -2.67
    .....
    -2.64
     superbly
    -2.64
    POSITIVE LOGITS
    퐿
    2.94
    鵙
    2.88
     specif
    2.88
    莇
    2.88
    ’
    2.86
    졍
    2.72
     semelh
    2.72
    跟她
    2.69
    姌
    2.66
    樒
    2.64
    Activations Density 0.011%

    No Known Activations