© 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. 44817
    Prev
    Next
    INDEX
    Explanations

    historical names and dates

    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
     they
    -2.59
     a
    -2.42
     in
    -2.09
     is
    -2.00
     tijdens
    -1.74
     inmiddels
    -1.64
    ⅰ
    -1.60
     the
    -1.59
    meuble
    -1.55
     Якщо
    -1.53
    POSITIVE LOGITS
    ↵
    1.90
    1
    1.84
    </h5>
    1.76
    甚至
    1.66
    de
    1.59
     but
    1.59
     jedoch
    1.57
     blissful
    1.54
     limitless
    1.53
     unusual
    1.52
    Activations Density 0.067%

    No Known Activations