© 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. 73278
    Prev
    Next
    INDEX
    Explanations

    quirkiest characters

    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
    طرف
    -1.66
    弒
    -1.54
     enormous
    -1.54
     slight
    -1.52
    ܼ
    -1.51
     flyg
    -1.48
    躰
    -1.48
     pollici
    -1.48
    Those
    -1.48
     світу
    -1.48
    POSITIVE LOGITS
     других
    1.58
     But
    1.51
     a
    1.50
     Перейти
    1.45
    ,{
    1.43
     otros
    1.43
     and
    1.42
    pope
    1.41
     muitos
    1.41
     The
    1.38
    Activations Density 0.082%

    No Known Activations