© 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. 10279
    Prev
    Next
    INDEX
    Explanations

    sequence or has

    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
     następnie
    -2.91
    푙
    -2.45
     прошлого
    -2.17
    ↵
    -2.16
     Fahrzeuge
    -2.14
     "")
    -2.14
    linawan
    -2.13
    -2.08
     czemu
    -2.06
    u
    -2.05
    POSITIVE LOGITS
    \
    2.38
    
    2.33
    もの
    2.30
    ции
    2.28
     måtte
    2.27
    واسطة
    2.23
     recargable
    2.20
    会有
    2.14
     Studying
    2.13
    嗵
    2.08
    Activations Density 0.001%

    No Known Activations