© 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. 128031
    Prev
    Next
    INDEX
    Explanations

    jquery $(function

    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
     andere
    -1.88
     alcune
    -1.63
     lác
    -1.53
    趿
    -1.52
    ptăm
    -1.48
     kommune
    -1.47
     the
    -1.47
    　(
    -1.45
    鍮
    -1.41
     vertus
    -1.40
    POSITIVE LOGITS
    伫
    1.70
    矗
    1.55
     halben
    1.55
     englischen
    1.54
     längere
    1.51
     vorigen
    1.51
     totalité
    1.50
     höheren
    1.50
     läßt
    1.45
     мужа
    1.45
    Activations Density 0.003%

    No Known Activations