© 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. 74286
    Prev
    Next
    INDEX
    Explanations

    author's content introduction

    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
     its
    -1.80
     your
    -1.70
     that
    -1.57
     if
    -1.52
     It
    -1.46
    ᱼ
    -1.45
     could
    -1.43
    In
    -1.41
     their
    -1.34
     may
    -1.34
    POSITIVE LOGITS
     tirs
    1.66
     rése
    1.58
     tille
    1.47
     fabrik
    1.47
     perles
    1.44
     publie
    1.43
     hek
    1.41
     ingrédients
    1.41
     juf
    1.38
     fers
    1.38
    Activations Density 0.156%

    No Known Activations