© 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. 34-GEMMASCOPE-RES-131K
    7. 32727
    Prev
    Next
    INDEX
    Explanations

    Austen, Hampshire, Mansfield Park

    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_34/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
    梦见
    -0.82
     trouser
    -0.74
     centenary
    -0.71
     strangely
    -0.70
    лым
    -0.70
     diverse
    -0.69
     oddly
    -0.69
     numerous
    -0.69
    Int
    -0.67
    ziesz
    -0.67
    POSITIVE LOGITS
     Portsmouth
    0.98
     voit
    0.89
    वान
    0.88
    Dash
    0.88
     Dash
    0.88
     Austen
    0.87
     Mansfield
    0.87
    
    0.86
     élégant
    0.86
     Hampshire
    0.86
    Activations Density 0.004%

    No Known Activations