© 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. 99882
    Prev
    Next
    INDEX
    Explanations

    Folio, manuscript, atlases

    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
    </b>
    -2.03
     you
    -1.50
    what
    -1.48
    {
    -1.39
    给予
    -1.38
    But
    -1.37
     about
    -1.35
    which
    -1.34
    やお
    -1.34
     unsur
    -1.32
    POSITIVE LOGITS
    </h3>
    1.67
    涜
    1.60
     conocidos
    1.57
     τῆς
    1.54
     conocidas
    1.52
    ᛫
    1.51
     religieux
    1.48
    翃
    1.45
    未完
    1.45
     elongated
    1.44
    Activations Density 0.003%

    No Known Activations