© 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. 60746
    Prev
    Next
    INDEX
    Explanations

    city followed by city name

    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
    \
    -2.09
     ランチ
    -1.90
    !!”
    -1.89
    苼
    -1.84
     الفلسطيني
    -1.77
    に向かって
    -1.70
     imageNamed
    -1.67
     weißem
    -1.66
    
    -1.66
    átiles
    -1.65
    POSITIVE LOGITS
     的
    2.14
     тебе
    2.00
     _,
    1.89
     була
    1.88
    ヶ月
    1.88
    )
    1.84
     lacking
    1.84
     jsou
    1.78
     Of
    1.75
     ʻ
    1.74
    Activations Density 0.013%

    No Known Activations