© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68312
    Prev
    Next
    INDEX
    Explanations

    scanners relies, features outweighs

    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_22/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
    人で
    -0.89
    gebühren
    -0.80
    має
    -0.80
     ")";
    -0.78
    boldmath
    -0.78
    氢
    -0.77
    なの
    -0.76
     Broth
    -0.74
    Inggris
    -0.73
    име
    -0.73
    POSITIVE LOGITS
     depends
    1.31
     ensured
    1.06
     depended
    0.94
     depend
    0.93
     reflected
    0.91
     AspNetCore
    0.91
     depende
    0.90
     եր
    0.88
     realized
    0.86
    noten
    0.84
    Activations Density 0.241%

    No Known Activations