© 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. 69586
    Prev
    Next
    INDEX
    Explanations

    name prefixes

    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
     at
    -2.70
     in
    -2.67
     during
    -2.53
     While
    -2.34
     two
    -2.34
     During
    -2.30
     Although
    -2.23
     to
    -2.22
     when
    -2.19
     Many
    -2.14
    POSITIVE LOGITS
     zoude
    2.50
    
    2.28
    趿
    2.20
    僦
    2.16
    粜
    2.02
     soooo
    1.99
    
    1.98
     ridiculously
    1.94
    ఽ
    1.92
    
    1.92
    Activations Density 0.056%

    No Known Activations