© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130068
    Prev
    Next
    INDEX
    Explanations

    times and durations

    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
     informaci
    -1.87
    4
    -1.77
     that
    -1.73
     έχουν
    -1.60
     your
    -1.56
    sometimes
    -1.52
     kontaktu
    -1.51
     mentre
    -1.49
     quando
    -1.48
     otot
    -1.47
    POSITIVE LOGITS
    出了一
    1.82
     of
    1.77
    ですが
    1.37
     "
    1.34
     jedoch
    1.32
    难过
    1.30
     interes
    1.28
    诂
    1.27
     
    1.27
     fiel
    1.24
    Activations Density 0.038%

    No Known Activations