© 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. 68965
    Prev
    Next
    INDEX
    Explanations

    his, new, he, are, guard, my, riot, the, tuesday, geo, learn

    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
    Y
    -2.70
    t
    -2.17
    L
    -2.02
    \
    -1.97
    P
    -1.92
    K
    -1.88
    F
    -1.88
    J
    -1.86
    U
    -1.83
    Z
    -1.80
    POSITIVE LOGITS
    ܊
    2.17
    葙
    2.03
    鵟
    1.97
    Mvh
    1.86
     iſt
    1.83
     lạt
    1.83
    鈇
    1.82
    każ
    1.81
    獁
    1.79
     turisti
    1.77
    Activations Density 0.118%

    No Known Activations