© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44135
    Prev
    Next
    INDEX
    Explanations

    surprising

    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
    D
    -2.09
    𖥧
    -1.99
    ଃ
    -1.96
    S
    -1.91
    N
    -1.88
     provisoire
    -1.84
     может
    -1.82
     jóvenes
    -1.80
    ne
    -1.78
    ?”
    -1.78
    POSITIVE LOGITS
    瑧
    2.23
     surprise
    2.22
    歘
    1.88
     белые
    1.87
    surprise
    1.85
     черные
    1.84
    Surprise
    1.78
    缡
    1.78
    いかがでしたか
    1.71
     Surprise
    1.70
    Activations Density 0.021%

    No Known Activations