© 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. 58737
    Prev
    Next
    INDEX
    Explanations

    some, many, certain

    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
    er
    -1.86
     القديمة
    -1.73
     وكان
    -1.65
     وكانت
    -1.64
    歩道
    -1.58
     الجديدة
    -1.55
     разли
    -1.54
    簓
    -1.52
    四个
    -1.52
     mantra
    -1.52
    POSITIVE LOGITS
     incluso
    1.99
     até
    1.96
     некоторых
    1.84
     Tbsp
    1.83
    尨
    1.80
     typu
    1.72
    ing
    1.71
    肫
    1.67
     многих
    1.66
     zustand
    1.66
    Activations Density 0.008%

    No Known Activations