© 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. 127852
    Prev
    Next
    INDEX
    Explanations

    long shot, contrary, opposite, moreover

    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
     with
    -1.56
     a
    -1.49
     for
    -1.48
     hjælpe
    -1.39
    with
    -1.37
    Jakie
    -1.34
    での
    -1.26
    اری
    -1.26
     [
    -1.24
    Uwaga
    -1.22
    POSITIVE LOGITS
     Ngày
    1.62
    ेंगे
    1.62
    mybatisplus
    1.54
    耵
    1.51
    嶇
    1.46
     république
    1.45
     pertes
    1.45
     estekak
    1.42
    ，“
    1.42
     tevreden
    1.41
    Activations Density 0.008%

    No Known Activations