© 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. 34-GEMMASCOPE-RES-131K
    7. 60130
    Prev
    Next
    INDEX
    Explanations

    comes as a surprise

    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
     came
    -1.29
     come
    -1.27
    Come
    -1.03
    came
    -0.95
     situação
    -0.90
     comes
    -0.90
     COME
    -0.89
     Come
    -0.85
    ḑ
    -0.84
     datang
    -0.84
    POSITIVE LOGITS
     surprise
    1.69
     shock
    1.58
     surprises
    1.11
    surprise
    1.05
     sho
    1.04
     Surprise
    1.02
    Shock
    0.96
    Surprise
    0.96
     große
    0.95
     shocks
    0.95
    Activations Density 0.011%

    No Known Activations