© 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. 58876
    Prev
    Next
    INDEX
    Explanations

    initialisms and abbreviations

    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
     It
    -2.95
    巿
    -2.52
    癀
    -2.50
     staunch
    -2.45
     vorüber
    -2.42
     Both
    -2.38
     Furthermore
    -2.36
    It
    -2.34
     postulated
    -2.34
    новые
    -2.31
    POSITIVE LOGITS
    s
    4.16
    t
    2.41
    ですが
    2.31
     dosen
    2.20
     nových
    2.16
    k
    2.09
     kutu
    2.08
    ka
    2.06
    N
    2.03
     tekno
    2.02
    Activations Density 0.222%

    No Known Activations