© 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. 34-GEMMASCOPE-RES-131K
    7. 92987
    Prev
    Next
    INDEX
    Explanations

    possessives and contractions

    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_34/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
    Authors
    -0.85
     improves
    -0.81
     generally
    -0.81
     Authors
    -0.80
     tror
    -0.80
     one
    -0.79
     谁
    -0.78
     or
    -0.77
     beni
    -0.77
     (
    -0.76
    POSITIVE LOGITS
     NFTs
    1.05
     COVID
    1.03
     covid
    1.02
    ᠭ
    0.96
     Covid
    0.96
     Biden
    0.94
     ChatGPT
    0.93
     macOS
    0.93
    ・・・・・
    0.93
     SECTIONS
    0.92
    Activations Density 0.013%

    No Known Activations