© 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. 70616
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or not knowing

    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
    亙
    -1.68
    榖
    -1.54
    使い方
    -1.54
    って何
    -1.51
     compéti
    -1.50
     journaling
    -1.49
    拄
    -1.49
    vänd
    -1.49
    棪
    -1.48
    嫆
    -1.48
    POSITIVE LOGITS
     HttpNotFound
    1.49
    0
    1.48
     we
    1.41
    we
    1.40
    le
    1.40
     been
    1.39
    s
    1.37
    la
    1.37
     again
    1.36
    ↵↵
    1.34
    Activations Density 0.005%

    No Known Activations