© 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. 113150
    Prev
    Next
    INDEX
    Explanations

    Miklos, The, blog, Q&A

    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
     Fakta
    -1.98
     Dokter
    -1.88
     Suara
    -1.88
    '
    -1.87
     Spes
    -1.87
    鯪
    -1.84
     Karakter
    -1.80
     hadapan
    -1.78
    难怪
    -1.77
     جات
    -1.75
    POSITIVE LOGITS
    to
    2.66
     he
    2.45
     “
    2.44
     This
    2.38
     
    2.16
    窳
    2.08
     "
    2.06
    o
    2.05
     distintas
    2.03
    </sub>
    2.02
    Activations Density 0.006%

    No Known Activations