© 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. 15052
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and matrices

    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
    了什么
    -1.80
    了一会儿
    -1.76
    %)$
    -1.76
    chargement
    -1.75
     andere
    -1.75
    了不少
    -1.73
     kleinere
    -1.72
    ᜀ
    -1.71
     ۱۱
    -1.70
    issipp
    -1.70
    POSITIVE LOGITS
     that
    2.30
     this
    2.17
     whose
    1.94
     in
    1.93
     When
    1.90
     with
    1.86
     which
    1.82
     to
    1.80
     during
    1.79
     at
    1.77
    Activations Density 0.084%

    No Known Activations