© 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. 22-GEMMASCOPE-RES-131K
    7. 35119
    Prev
    Next
    INDEX
    Explanations

    expressing surprise or shock

    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_22/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
     Glied
    -0.98
    uan
    -0.93
     currently
    -0.92
    uta
    -0.91
    Specifier
    -0.90
    antism
    -0.89
     penso
    -0.88
    naires
    -0.86
    による
    -0.85
     нужно
    -0.84
    POSITIVE LOGITS
     surprised
    1.77
     surprise
    1.77
     Surprise
    1.62
    surprise
    1.59
     surprises
    1.55
    unexpected
    1.52
     unexpected
    1.48
     surprising
    1.41
    Surprise
    1.30
     surpre
    1.23
    Activations Density 0.048%

    No Known Activations