© 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. 128145
    Prev
    Next
    INDEX
    Explanations

    current date, time, or PID

    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
     wondrous
    -1.89
    讦
    -1.66
     AMAZING
    -1.66
     pittores
    -1.58
     appré
    -1.57
    Everyday
    -1.55
    📉
    -1.55
     treff
    -1.53
     schild
    -1.52
     accompagné
    -1.51
    POSITIVE LOGITS
     for
    2.81
     not
    2.45
     because
    2.44
     after
    2.42
     should
    2.36
     from
    2.27
     will
    2.23
     now
    2.16
     while
    2.14
     that
    2.11
    Activations Density 0.048%

    No Known Activations